3.3k citations · 4.2k across the 69 of their papers we have counts for
25 papers · 1 filter
On Counterfactual Data Augmentation Under Confounding
Abbavaram Gowtham Reddy, Saketh Bachu, Saloni Dash +3
Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to var…
Towards Learning and Explaining Indirect Causal Effects in Neural Networks
Abbavaram Gowtham Reddy, Saketh Bachu, Harsharaj Pathak +4
Recently, there has been a growing interest in learning and explaining causal effects within Neural Network (NN) models. By virtue of NN architectures, previous approaches consider…
Towards Estimating Transferability using Hard Subsets
Tarun Ram Menta, Surgan Jandial, Akash Patil +6
As transfer learning techniques are increasingly used to transfer knowledge from the source model to the target task, it becomes important to quantify which source models are suita…
On the Robustness of Explanations of Deep Neural Network Models: A Survey
Amlan Jyoti, Karthik Balaji Ganesh, Manoj Gayala +3
Explainability has been widely stated as a cornerstone of the responsible and trustworthy use of machine learning models. With the ubiquitous use of Deep Neural Network (DNN) model…
Counterfactual Generation Under Confounding
Abbavaram Gowtham Reddy, Saloni Dash, Amit Sharma +1
A machine learning model, under the influence of observed or unobserved confounders in the training data, can learn spurious correlations and fail to generalize when deployed. For…
Learning Modular Structures That Generalize Out-of-Distribution
Arjun Ashok, Chaitanya Devaguptapu, Vineeth Balasubramanian
Out-of-distribution (O.O.D.) generalization remains to be a key challenge for real-world machine learning systems. We describe a method for O.O.D. generalization that, through trai…
On Causally Disentangled Representations
Abbavaram Gowtham Reddy, Benin Godfrey L, Vineeth N Balasubramanian
Representation learners that disentangle factors of variation have already proven to be important in addressing various real world concerns such as fairness and interpretability. I…
Matching Learned Causal Effects of Neural Networks with Domain Priors
Sai Srinivas Kancheti, Abbavaram Gowtham Reddy, Vineeth N Balasubramanian +1
A trained neural network can be interpreted as a structural causal model (SCM) that provides the effect of changing input variables on the model's output. However, if training data…
Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approach
Anindya Sarkar, Anirban Sarkar, Sowrya Gali +1
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…
A Framework for Learning Ante-hoc Explainable Models via Concepts
Anirban Sarkar, Deepak Vijaykeerthy, Anindya Sarkar +1
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 gen…
Instance-wise Causal Feature Selection for Model Interpretation
Pranoy Panda, Sai Srinivas Kancheti, Vineeth N Balasubramanian
We formulate a causal extension to the recently introduced paradigm of instance-wise feature selection to explain black-box visual classifiers. Our method selects a subset of input…
Improving Attribution Methods by Learning Submodular Functions
Piyushi Manupriya, Tarun Ram Menta, J. Saketha Nath +1
This work explores the novel idea of learning a submodular scoring function to improve the specificity/selectivity of existing feature attribution methods. Submodular scores are na…
A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization
Adepu Ravi Sankar, Yash Khasbage, Rahul Vigneswaran +1
Loss landscape analysis is extremely useful for a deeper understanding of the generalization ability of deep neural network models. In this work, we propose a layerwise loss landsc…
On Initial Pools for Deep Active Learning
Akshay L Chandra, Sai Vikas Desai, Chaitanya Devaguptapu +1
Active Learning (AL) techniques aim to minimize the training data required to train a model for a given task. Pool-based AL techniques start with a small initial labeled pool and t…
On Adversarial Robustness: A Neural Architecture Search perspective
Chaitanya Devaguptapu, Devansh Agarwal, Gaurav Mittal +2
Adversarial robustness of deep learning models has gained much traction in the last few years. Various attacks and defenses are proposed to improve the adversarial robustness of mo…
On the benefits of defining vicinal distributions in latent space
Puneet Mangla, Vedant Singh, Shreyas Jayant Havaldar +1
The vicinal risk minimization (VRM) principle is an empirical risk minimization (ERM) variant that replaces Dirac masses with vicinal functions. There is strong numerical and theor…
Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks
Sandesh Kamath, Amit Deshpande, K V Subrahmanyam +1
(Non-)robustness of neural networks to small, adversarial pixel-wise perturbations, and as more recently shown, to even random spatial transformations (e.g., translations, rotation…
A Little Fog for a Large Turn
Harshitha Machiraju, Vineeth N Balasubramanian
Small, carefully crafted perturbations called adversarial perturbations can easily fool neural networks. However, these perturbations are largely additive and not naturally found.…
Charting the Right Manifold: Manifold Mixup for Few-shot Learning
Puneet Mangla, Mayank Singh, Abhishek Sinha +3
Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes with the help of only a few labeled examples. A recent regularization technique - M…
Harnessing the Vulnerability of Latent Layers in Adversarially Trained Models
Mayank Singh, Abhishek Sinha, Nupur Kumari +3
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective…
Submodular Batch Selection for Training Deep Neural Networks
K J Joseph, Vamshi Teja R, Krishnakant Singh +1
Mini-batch gradient descent based methods are the de facto algorithms for training neural network architectures today. We introduce a mini-batch selection strategy based on submodu…
Neural Network Attributions: A Causal Perspective
Aditya Chattopadhyay, Piyushi Manupriya, Anirban Sarkar +1
We propose a new attribution method for neural networks developed using first principles of causality (to the best of our knowledge, the first such). The neural network architectur…
DANTE: Deep AlterNations for Training nEural networks
Vaibhav B Sinha, Sneha Kudugunta, Adepu Ravi Sankar +3
We present DANTE, a novel method for training neural networks using the alternating minimization principle. DANTE provides an alternate perspective to traditional gradient-based ba…
On the Analysis of Trajectories of Gradient Descent in the Optimization of Deep Neural Networks
Adepu Ravi Sankar, Vishwak Srinivasan, Vineeth N Balasubramanian
Theoretical analysis of the error landscape of deep neural networks has garnered significant interest in recent years. In this work, we theoretically study the importance of noise…