publications
List of Publications in reversed chronological order.
2026
- NeurIPSAdapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial DiscoveryJowaria Khan, Anindya Sarkar, Yevgeniy Vorobeychik, and Elizabeth Bondi-KellyIn the 40th Neural Information Processing Systems, 2026, Atlanta, USA, Dec 2026
In environmental monitoring, data collection is often costly, sparse, and shaped by urgent public-health needs. This is particularly true for cancer-causing PFAS (Per- and polyfluoroalkyl substances) contamination, where discussions with domain experts and environmental organizations highlight the need to strategically identify high-risk, under-observed regions under tight sampling budgets. More broadly, similar challenges arise in disaster response and public health settings, where dynamic environments make it essential to efficiently uncover hidden targets from limited ground truth. Yet sparse and biased geospatial labels limit the applicability of existing learning-based methods, such as reinforcement learning. To address this, we propose a unified geospatial discovery framework that integrates active learning, online meta-learning, and concept-guided reasoning. Our approach introduces two key innovations built on a shared notion of concept relevance, capturing how domain-specific factors influence target presence: a concept-weighted uncertainty sampling strategy, where uncertainty is modulated by learned relevance from readily available concepts such as land cover and source proximity; and a relevance-aware meta-batch formation strategy that promotes semantic diversity during online-meta updates, improving generalization in dynamic environments. We evaluate our framework on PFAS contamination discovery as a real-world inspired environmental monitoring task, demonstrating robust target discovery under limited data and changing conditions.
- NeurIPS WorkshopLATS: Levy Adaptive Tree Sampling for Feedback-Driven Diverse Target DiscoveryBinglin Ji, Anindya Sarkar, Hengchang Lu, Lecheng Kong, and 2 more authorsIn the NeurIPS Workshop on "AI for Stochastic Dynamics", 2026, Sydney, Australia, Dec 2026
While diffusion models excel at capturing complex data distributions, scientific discovery often requires steering generation toward specific, uncharacterized regions that maximize a target objective. These high-utility modes frequently reside in low-likelihood tail regions and are only revealed sequentially through interactive feedback. Existing diffusion samplers fail in this regime: they inherit the pre-trained model’s bias toward high-density regions, leaving rare yet promising phenomena underexplored. Conversely, exploration-heavy samplers ensure broad coverage but fail to efficiently exploit high-utility modes when constrained by a strict sampling budget. To resolve this dilemma, we introduce Levy Adaptive Tree Search (LATS), a principled sampling framework for online feedback-driven search. LATS leverages heavy-tailed exploration coupled with tree-based value backpropagation to progressively uncover preferred modes. By maintaining broad distributional coverage, LATS successfully discovers low-likelihood, high-utility regions while preserving sample fidelity and structural diversity. Experiments across diverse benchmarks, including materials science, demonstrate that LATS significantly outperforms baselines in target discovery efficiency.
- ECML PKDDPAPA: Online Personalized Active Preference AlignmentAnindya Sarkar, Nasik Muhammad Nafi, Isaac Lyngaas, Muralikrishnan Gopalakrishnan Meena, and 1 more authorIn the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2026, Naples, Sep 2026
Diffusion models are highly effective at modeling complex data distributions, including images and text. However, in applications like personalized recommender systems, the objective often shifts to modeling specific regions of the distribution that maximize user preferences-initially unknown but gradually uncovered through interactive feedback. This can naturally be framed as a reinforcement learning problem, where the goal is to fine-tune a diffusion model to maximize a reward function based on preferences. However, the main challenge lies in learning a parameterized reward model, which typically requires large-scale preference data-something that is often not feasible in practice. In this work, we introduce Personalized Active Preference Alignment PAPA, a novel method that bypasses the requirement for a parametrized reward model by directly optimizing the diffusion model using real-time user feedback. PAPA enables feedback-efficient preference alignment, drawing inspiration from the variational inference framework. We demonstrate PAPA’s effectiveness through extensive experiments and ablation studies across diverse class-conditioned and fine-grained alignment tasks. Additionally, based on theoretical insights, we propose an enhanced fine-tuning strategy, referred to as EPAPA, that requires less computational budget and accelerates the fine-tuning process, further boosting PAPA’s suitability for real-world deployment.
- AAMASDiffVAS: Diffusion-Guided Visual Active Search in Partially Observable EnvironmentsAnindya Sarkar, Srikumar Sastry, Aleksis Pirinen, Nathan Jacobs, and 1 more authorIn the 25th International Conference on Autonomous Agents and Multiagent Systems, 2026, Paphos, May 2026
Visual active search (VAS) has been introduced as a modeling framework that leverages visual cues to direct aerial (e.g., UAV-based) exploration and pinpoint areas of interest within extensive geospatial regions. Prior VAS approaches assume the entire search space is known upfront, which is often unrealistic due to constraints such as a restricted field of view and high acquisition costs, and they typically learn policies tailored to specific target objects, limiting their ability to search for multiple target categories simultaneously. We propose DiffVAS, a target-conditioned policy that enables simultaneous search for diverse objects in partially observable environments. DiffVAS consists of two key modules: a diffusion-based conditional generative module (CGM) and a target-conditioned planning module (TCPM). DiffVAS leverages a diffusion model to reconstruct the entire geospatial area from sequentially observed partial glimpses, which enables the target-conditioned reinforcement learning-based planning module to effectively reason and guide subsequent search steps. Extensive experiments on satellite imagery datasets demonstrate that DiffVAS excels in searching diverse objects in partially observable environments, significantly surpassing state-of-the-art methods.
2025
- NeurIPSActive Target Discovery under Uninformative Prior: The Power of Permanent and Transient MemoryAnindya Sarkar, Binglin Ji, and Yevgeniy VorobeychikIn the 39th Neural Information Processing Systems, 2025, San Diego, Dec 2025
In many scientific and engineering fields, where acquiring high-quality data is expensive–such as medical imaging, environmental monitoring, and remote sensing–strategic sampling of unobserved regions based on prior observations is crucial for maximizing discovery rates within a constrained budget. The rise of powerful generative models, such as diffusion models, has enabled active target discovery in partially observable environments by leveraging learned priors–probabilistic representations that capture underlying structure from data. With guidance from sequentially gathered task-specific observations, these models can progressively refine exploration and efficiently direct queries toward promising regions. However, in domains where learning a strong prior is infeasible due to extremely limited data or high sampling cost (such as rare species discovery, diagnostics for emerging diseases, etc.), these methods struggle to generalize. To overcome this limitation, we propose a novel approach that enables effective active target discovery even in settings with uninformative priors, ensuring robust exploration and adaptability in complex real-world scenarios. Our framework is theoretically principled and draws inspiration from neuroscience to guide its design. Unlike black-box policies, our approach is inherently interpretable, providing clear insights into decision-making. Furthermore, it guarantees a strong, monotonic improvement in prior estimates with each new observation, leading to increasingly accurate sampling and reinforcing both reliability and adaptability in dynamic settings. Through comprehensive experiments and ablation studies across various domains, including species distribution modeling and remote sensing, we demonstrate that our method substantially outperforms baseline approaches.
- NeurIPSOnline Feedback Efficient Active Target Discovery in Partially Observable EnvironmentsAnindya Sarkar, Binglin Ji, and Yevgeniy VorobeychikIn the 39th Neural Information Processing Systems, 2025, San Diego, Dec 2025
In various scientific and engineering domains, where data acquisition is costly–such as in medical imaging, environmental monitoring, or remote sensing–strategic sampling from unobserved regions, guided by prior observations, is essential to maximize target discovery within a limited sampling budget. In this work, we introduce Diffusion-guided Active Target Discovery (DiffATD), a novel method that leverages diffusion dynamics for active target discovery. DiffATD maintains a belief distribution over each unobserved state in the environment, using this distribution to dynamically balance exploration-exploitation. Exploration reduces uncertainty by sampling regions with the highest expected entropy, while exploitation targets areas with the highest likelihood of discovering the target, indicated by the belief distribution and an incrementally trained reward model designed to learn the characteristics of the target. DiffATD enables efficient target discovery in a partially observable environment within a fixed sampling budget, all without relying on any prior supervised training. Furthermore, DiffATD offers interpretability, unlike existing black–box policies that require extensive supervised training. Through extensive experiments and ablation studies across diverse domains, including medical imaging, species discovery, and remote sensing, we show that DiffATD performs significantly better than baselines and competitively with supervised methods that operate under full environmental observability.
- ICMLLearning Policy Committees for Effective Personalization in MDPs with Diverse TasksLuise Ge, Michael Lanier, Anindya Sarkar, Bengisu Guresti, and 2 more authorsIn the 42nd International Conference on Machine Learning, 2025, Vancouver, Jul 2025
Many dynamic decision problems, such as robotic control, involve a series of tasks, many of which are unknown at training time. Typical approaches for these problems, such as multi-task and meta reinforcement learning, do not generalize well when the tasks are diverse. On the other hand, approaches that aim to tackle task diversity, such as using task embedding as policy context and task clustering, typically lack performance guarantees and require a large number of training tasks. To address these challenges, we propose a novel approach for learning a policy committee that includes at least one near-optimal policy with high probability for tasks encountered during execution. While we show that this problem is in general inapproximable, we present two practical algorithmic solutions. The first yields provable approximation and task sample complexity guarantees when tasks are low-dimensional (the best we can do due to inapproximability), whereas the second is a general and practical gradient-based approach. In addition, we provide a provable sample complexity bound for few-shot learning. Our experiments on MuJoCo and Meta-World show that the proposed approach outperforms state-of-the-art multi-task, meta-, and task clustering baselines in training, generalization, and few-shot learning, often by a large margin.
- AAAIActive Geospatial Search for Efficient Tenant Eviction OutreachAnindya Sarkar, Alex DiChristofano, Sanmay Das, Patrick Fowler, and 2 more authorsIn the 39th AAAI Conference on Artificial Intelligence, 2025, Philadelphia, Feb 2025
Tenant evictions threaten housing stability and are a major concern for many cities. An open question concerns whether data-driven methods enhance outreach programs that target at-risk tenants to mitigate their risk of eviction. We propose a novel active geospatial search (AGS) modeling framework for this problem. AGS integrates property-level information in a search policy that identifies a sequence of rental units to canvas to both determine their eviction risk and provide support if needed. We propose a hierarchical reinforcement learning approach to learn a search policy for AGS that scales to large urban areas containing thousands of parcels, balancing exploration and exploitation and accounting for travel costs and a budget constraint. Crucially, the search policy adapts online to newly discovered information about evictions. Evaluation using eviction data for a large urban area demonstrates that the proposed framework and algorithmic approach are considerably more effective at sequentially identifying eviction cases than baseline methods.
2024
- NeurIPSGOMAA-Geo: GOal Modality Agnostic Active Geo-localizationAnindya Sarkar, Srikumar Sastry, Aleksis Pirinen, Chongjie Zhang, and 2 more authorsIn the 38th Neural Information Processing Systems, 2024, Vancouver, Dec 2024
We consider the task of active geo-localization (AGL) in which an agent uses a sequence of visual cues observed during aerial navigation to find a target specified through multiple possible modalities. This could emulate a UAV involved in a search-and-rescue operation navigating through an area, observing a stream of aerial images as it goes. The AGL task is associated with two important challenges. Firstly, an agent must deal with a goal specification in one of multiple modalities (e.g., through a natural language description) while the search cues are provided in other modalities (aerial imagery). The second challenge is limited localization time (e.g., limited battery life, urgency) so that the goal must be localized as efficiently as possible, i.e. the agent must effectively leverage its sequentially observed aerial views when searching for the goal. To address these challenges, we propose GOMAA-Geo - a goal modality agnostic active geo-localization agent - for zero-shot generalization between different goal modalities. Our approach combines cross-modality contrastive learning to align representations across modalities with supervised foundation model pretraining and reinforcement learning to obtain highly effective navigation and localization policies. Through extensive evaluations, we show that GOMAA-Geo outperforms alternative learnable approaches and that it generalizes across datasets - e.g., to disaster-hit areas without seeing a single disaster scenario during training - and goal modalities - e.g., to ground-level imagery or textual descriptions, despite only being trained with goals specified as aerial views.
- WACVA Visual Active Search Framework for Geospatial ExplorationAnindya Sarkar, Michael Lanier, Alfeld Scott, Jiarui Feng, and 3 more authorsIn the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024, Hawaii, Jan 2024
Many problems can be viewed as forms of geospatial search aided by aerial imagery, with examples ranging from detecting poaching activity to human trafficking. We model this class of problems in a visual active search (VAS) framework, which has three key inputs: (1) an image of the entire search area, which is subdivided into regions, (2) a local search function, which determines whether a previously unseen object class is present in a given region, and (3) a fixed search budget, which limits the number of times the local search function can be evaluated. The goal is to maximize the number of objects found within the search budget. We propose a reinforcement learning approach for VAS that learns a meta-search policy from a collection of fully annotated search tasks. This meta-search policy is then used to dynamically search for a novel target-object class, leveraging the outcome of any previous queries to determine where to query next. Through extensive experiments on several large-scale satellite imagery datasets, we show that the proposed approach significantly outperforms several strong baselines. We also propose novel domain adaptation techniques that improve the policy at decision time when there is a significant domain gap with the training data. Code is publicly available.
- AAMASGeospatial Active Search for Preventing EvictionsAnindya Sarkar, Alex Dichristofano, Sanmay Das, Patrick Fowler, and 2 more authorsIn the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024, Auckland, May 2024
Evictions are a threat to housing stability and a major concern for many cities. An open question is whether data-driven methods can enhance door-to-door outreach programs to target at-risk tenants. We model this problem using a new framework we term geospatial active search. Geospatial Active Search integrates visual information such as satellite imagery along with tabular data such as property and neighborhood-level information to create an online exploration plan. We develop an approach for the implementation of Geospatial Active Search in St. Louis to find properties containing tenants who will have an eviction filed against them.
- AAAI WorkshopAttacks on Node Attributes in Graph Neural NetworksXu Ying, Michael Lanier, Anindya Sarkar, and Yevgeniy VorobeychikIn the AAAI Workshop on "AI for Cyber Security", 2024, Vancouver, Mar 2024
Graphs are commonly used to model complex networks prevalent in modern social media and literacy applications. Our research investigates the vulnerability of these graphs through the application of feature based adversarial attacks, focusing on both decision-time attacks and poisoning attacks. In contrast to state-of-the-art models like Net Attack and Meta Attack, which target node attributes and graph structure, our study specifically targets node attributes. For our analysis, we utilized the text dataset Hellaswag and graph datasets Cora and CiteSeer, providing a diverse basis for evaluation. Our findings indicate that decision-time attacks using Projected Gradient Descent (PGD) are more potent compared to poisoning attacks that employ Mean Node Embeddings and Graph Contrastive Learning strategies. This provides insights for graph data security, pinpointing where graph-based models are most vulnerable and thereby informing the development of stronger defense mechanisms against such attacks.
2023
- NeurIPSA Partially-Supervised Reinforcement Learning Framework for Visual Active SearchAnindya Sarkar, Nathan Jacobs, and Yevgeniy VorobeychikIn the 37th Neural Information Processing Systems, 2023, New Orleans, Dec 2023
Visual active search (VAS) has been proposed as a modeling framework in which visual cues are used to guide exploration, with the goal of identifying regions of interest in a large geospatial area. Its potential applications include identifying hotspots of rare wildlife poaching activity, search-and-rescue scenarios, identifying illegal trafficking of weapons, drugs, or people, and many others. State of the art approaches to VAS include applications of deep reinforcement learning (DRL), which yield end-to-end search policies, and traditional active search, which combines predictions with custom algorithmic approaches. While the DRL framework has been shown to greatly outperform traditional active search in such domains, its end-to-end nature does not make full use of supervised information attained either during training, or during actual search, a significant limitation if search tasks differ significantly from those in the training distribution. We propose an approach that combines the strength of both DRL and conventional active search by decomposing the search policy into a prediction module, which produces a geospatial distribution of regions of interest based on task embedding and search history, and a search module, which takes the predictions and search history as input and outputs the search distribution. We develop a novel meta-learning approach for jointly learning the resulting combined policy that can make effective use of supervised information obtained both at training and decision time. Our extensive experiments demonstrate that the proposed representation and meta-learning frameworks significantly outperform state of the art in visual active search on several problem domains.
2022
- NeurIPSHow powerful are K-hop message passing graph neural networksJiarui Feng, Yixin Chen, Fuhai Li, Anindya Sarkar, and 1 more authorIn the 36th Neural Information Processing Systems, 2022, New Orleans, Dec 2022
The most popular design paradigm for Graph Neural Networks (GNNs) is 1-hop message passing—aggregating information from 1-hop neighbors repeatedly. However, the expressive power of 1-hop message passing is bounded by the WeisfeilerLehman (1-WL) test. Recently, researchers extended 1-hop message passing to K-hop message passing by aggregating information from K-hop neighbors of nodes simultaneously. However, there is no work on analyzing the expressive power of K-hop message passing. In this work, we theoretically characterize the expressive power of K-hop message passing. Specifically, we first formally differentiate two different kernels of K-hop message passing which are often misused in previous works. We then characterize the expressive power of K-hop message passing by showing that it is more powerful than 1-WL and can distinguish almost all regular graphs. Despite the higher expressive power, we show that K-hop message passing still cannot distinguish some simple regular graphs and its expressive power is bounded by 3-WL. To further enhance its expressive power, we introduce a KP-GNN framework, which improves K-hop message passing by leveraging the peripheral subgraph information in each hop. We show that KP-GNN can distinguish many distance regular graphs which could not be distinguished by previous distance encoding or 3-WL methods. Experimental results verify the expressive power and effectiveness of KP-GNN. KP-GNN achieves competitive results across all benchmark datasets.
- CVPRA Framework for Learning Ante-hoc Explainable Models via ConceptsAnirban Sarkar, Deepak Vijaykeerthy, Anindya Sarkar, and Vineeth BalasubramanianIn the IEEE / CVF Computer Vision and Pattern Recognition Conference, 2022, New Orleans, Jun 2022
Self-explaining deep models are designed to learn the latent concept-based explanations implicitly during training, which eliminates the requirement of any post-hoc explanation generation technique. In this work, we propose one such model that appends an explanation generation module on top of any basic network and jointly trains the whole module that shows high predictive performance and generates meaningful explanations in terms of concepts. Our training strategy is suitable for unsupervised concept learning with much lesser parameter space requirements compared to baseline methods. Our proposed model also has provision for leveraging self-supervision on concepts to extract better explanations. However, with full concept supervision, we achieve the best predictive performance compared to recently proposed concept-based explainable models. We report both qualitative and quantitative results with our method, which shows better performance than recently proposed concept-based explainability methods. We reported exhaustive results with two datasets without ground truth concepts, i.e., CIFAR10, ImageNet, and two datasets with ground truth concepts, i.e., AwA2, CUB-200, to show the effectiveness of our method for both cases. To the best of our knowledge, we are the first ante-hoc explanation generation method to show results with a large-scale dataset such as ImageNet.
- WACVLeveraging Test-Time Consensus Prediction for Robustness against Unseen NoiseAnindya Sarkar, Anirban Sarkar, and Vineeth BalasubramanianIn the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022, Hawaii, Oct 2022
We propose a method to improve DNN robustness against unseen noisy corruptions, such as Gaussian noise, Shot Noise, Impulse Noise, Speckle noise with different levels of severity by leveraging ensemble technique through a consensus based prediction method using self-supervised learning at inference time. We also propose to enhance the model training by considering other aspects of the issue i.e. noise in data and better representation learning which shows even better generalization performance with the consensus based prediction strategy. We report results of each noisy corruption on the standard CIFAR10-C and ImageNet-C benchmark which shows significant boost in performance over previous methods. We also introduce results for MNIST-C and TinyImagenet-C to show usefulness of our method across datasets of different complexities to provide robustness against unseen noise. We show results with different architectures to validate our method against other baseline methods, and also conduct experiments to show the usefulness of each part of our method.
- GAMESECReward Delay Attacks on Deep Reinforcement LearningAnindya Sarkar, Jiarui Feng, Yevgeniy Vorobeychik, Christopher Gill, and 1 more authorIn the 13th Conference on Decision and Game Theory for Security, 2022, Pittsburgh, Oct 2022
Most reinforcement learning algorithms implicitly assume strong synchrony. We present novel attacks targeting Q-learning that exploit a vulnerability entailed by this assumption by delaying the reward signal for a limited time period. We consider two types of attack goals: targeted attacks, which aim to cause a target policy to be learned, and untargeted attacks, which simply aim to induce a policy with a low reward. We evaluate the efficacy of the proposed attacks through a series of experiments. Our first observation is that reward-delay attacks are extremely effective when the goal is simply to minimize reward. Indeed, we find that even naive baseline reward-delay attacks are also highly successful in minimizing the reward. Targeted attacks, on the other hand, are more challenging, although we nevertheless demonstrate that the proposed approaches remain highly effective at achieving the attacker’s targets. In addition, we introduce a second threat model that captures a minimal mitigation that ensures that rewards cannot be used out of sequence. We find that this mitigation remains insufficient to ensure robustness to attacks that delay, but preserve the order, of rewards.
- ECCV WorkshopEmpowering a Robust Model with Stable and Object-Aligned ExplanationsSowrya Gali, Anindya Sarkar, and Vineeth BalasubramanianIn the European Conference on Computer Vision Workshop on "Adversarial Robustness In The Real World", 2022, Tel Aviv, Oct 2022
The current state-of-the-art adversarially robust models have more object-aligned attributions, and attributionally robust models have stabler attributions than adversarially trained models. However, these robust models’ attributions suffer from another stability-alignment tradeoff problem, i.e., these models’ attributions are either stable against explanation-based attacks like IFIA at the cost of relevance or have well object-aligned attributions but unstable against the explanation-based attacks. We propose a training strategy that enforces attribution alignment through teacher saliency within the robust attribution training framework to curb this tradeoff. Moreover, we also note that the current evaluation metrics for measuring the stability of the attribution maps do not consider the object alignment of the generated attribution map and propose new metrics that capture both facets of the attribution maps, i.e., stability and alignment.
2021
- NeurIPSGet Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning ApproachAnindya Sarkar, Anirban Sarkar, Sowrya Gali, and Vineeth BalasubramanianIn the 35th Neural Information Processing Systems, 2021, Vancouver, Dec 2021
Current SOTA adversarially robust models are mostly based on adversarial training (AT) and differ only by some regularizers either at inner maximization or outer minimization steps. Being repetitive in nature during the inner maximization step, they take a huge time to train. We propose a non-iterative method that enforces the following ideas during training. Attribution maps are more aligned to the actual object in the image for adversarially robust models compared to naturally trained models. Also, the allowed set of pixels to perturb an image (that changes model decision) should be restricted to the object pixels only, which reduces the attack strength by limiting the attack space. Our method achieves significant performance gains with a little extra effort (10-20%) over existing AT models and outperforms all other methods in terms of adversarial as well as natural accuracy. We have performed extensive experimentation with CIFAR-10, CIFAR-100, and TinyImageNet datasets and reported results against many popular strong adversarial attacks to prove the effectiveness of our method.
- AAAIEnhanced Regularizers for Attributional RobustnessAnindya Sarkar, Anirban Sarkar, and Vineeth BalasubramanianIn the 35th AAAI Conference on Artificial Intelligence, 2021, Vancouver, Feb 2021
Deep neural networks are the default choice of learning models for computer vision tasks. Extensive work has been carried out in recent years on explaining deep models for vision tasks such as classification. However, recent work has shown that it is possible for these models to produce substantially different attribution maps even when two very similar images are given to the network, raising serious questions about trustworthiness. To address this issue, we propose a robust attribution training strategy to improve attributional robustness of deep neural networks. Our method carefully analyzes the requirements for attributional robustness and introduces two new regularizers that preserve a model’s attribution map during attacks. Our method surpasses state-of-the-art attributional robustness methods by a margin of approximately 3% to 9% in terms of attribution robustness measures on several datasets including MNIST, FMNIST, Flower and GTSRB.
2020
- ICANNEnforcing Linearity in DNN succours Robustness and Adversarial Image GenerationAnindya Sarkar, and Raghu IyengarIn the 29th International Conference on Artificial Neural Network, 2020, Slovakia, Sep 2020
Recent studies on the adversarial vulnerability of neural networks have shown that models trained with the objective of minimizing an upper bound on the worst-case loss over all possible adversarial perturbations improve robustness against adversarial attacks. Beside exploiting adversarial training framework, we show that by enforcing a Deep Neural Network (DNN) to be linear in transformed input and feature space improves robustness significantly. We also demonstrate that by augmenting the objective function with Local Lipschitz regularizer boost robustness of the model further. Our method outperforms most sophisticated adversarial training methods and achieves state of the art adversarial accuracy on MNIST, CIFAR10 and SVHN dataset. In this paper, we also propose a novel adversarial image generation method by leveraging Inverse Representation Learning and Linearity aspect of an adversarially trained deep neural network classifier.
- ECCV WorkshopInducing Semantic Grouping of Latent Concepts for Explanations: An Ante-Hoc ApproachAnirban Sarkar, Deepak Vijaykeerthy, Anindya Sarkar, and Vineeth BalasubramanianIn the ECCV Workshop, 2020, Glasgow, Sep 2020
Self-explainable deep models are devised to represent the hidden concepts in the dataset without requiring any posthoc explanation generation technique. We worked with one of such models motivated by explicitly representing the classifier function as a linear function and showed that by exploiting probabilistic latent and properly modifying different parts of the model can result better explanation as well as provide superior predictive performance. Apart from standard visualization techniques, we proposed a new technique which can strengthen human understanding towards hidden concepts. We also proposed a technique of using two different self-supervision techniques to extract meaningful concepts related to the type of self-supervision considered and achieved significant performance boost. The most important aspect of our method is that it works nicely in a low data regime and reach the desired accuracy in a few number of epochs. We reported exhaustive results with CIFAR10, CIFAR100 and AWA2 datasets to show effect of our method with moderate and relatively complex datasets
- ICMLAODE guided Neural Data Augmentation Techniques for Time Series Data and its Benefits on RobustnessAnindya Sarkar, Anirudh Raj, and Raghu IyengarIn the 19th International Conference on Machine Learning and Applications, 2020, Florida, Dec 2020
Exploring adversarial attack vectors and studying their effects on machine learning algorithms has been of interest to researchers. Deep neural networks working with time series data have received lesser interest compared to their image counterparts in this context. In a recent finding, it has been revealed that current state-of-the-art deep learning time series classifiers are vulnerable to adversarial attacks. In this paper, we introduce two local gradient based and one spectral density based time series data augmentation techniques. We show that a model trained with data obtained using our techniques obtains state-of-the-art classification accuracy on various time series benchmarks. In addition, it improves the robustness of the model against some of the most common corruption techniques,such as Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM).
2019
- NLPIRZero-Shot Multilingual Sentiment Analysis using Hierarchical Attentive Network and BERTAnindya Sarkar, Sujeeth Reddy, and Raghu IyengarIn the 3rd International Conference on Natural Language Processing and Information Retrieval, 2019, Tokushima, Jun 2019
Sentiment analysis is considered an important downstream task in language modelling. We propose Hierarchical Attentive Network using BERT for document sentiment classification. We further showed that importing representation from Multiplicative LSTM model in our architecture results in faster convergence. We then propose a method to build a sentiment classifier for a language in which we have no labelled sentiment data. We exploit the possible semantic invariance across languages in the context of sentiment to achieve this.
- NeuroinformaticsCurated model development using NEUROiD: A web-based NEUROmotor integration and Design platformAnindya SarkarIn the Frontiers in Neuroinformatics, 2019, Jun 2019
The explosive growth in imaging technologies has been matched by an extraordinary increase in the number of investigations focusing on the structural and functional organization of the human spinal cord. The construction of comprehensive spinal cord atlases and databases of 3-dimensional spinal cord maps are very helpful in the field of neurological treatment and surgical analytics. Some of the notable ones among these Atlases are MRI Based Atlases,Cryoimaging Atlases,Multi-modality Atlases etc. But these Atlases are passive images that show the distribution of different anatomical or functional aspects. We aim to build a neurophysiology simulator of the relevant circuits in 3D anatomical coordinates that embody the biophysical knowledge. After superimposing this simulator on available Atlases or functional imagery like MRI.A clinician can ask questions on the functional implication of a procedure or the potential etiologies for a manifest condition. Further a systems analysis of the connectivities can provide clues to identification of network motifs responsible for oscillations and pattern generators. Towards this end we are making a realistic 3 dimensional model of a human spinal cord using NeuroConstruct and NEURON Simulation environment. The construction of such a 3D model involves identification of neuron biophysics, connectivities,cell types,synaptic Mechanisms, Channel Mechanisms,Morphology, Dendritic Architectures,locations.