429 citations · 678 across the 10 of their papers we have counts for
11 papers
Causal ATE Mitigates Unintended Bias in Controlled Text Generation
Rahul Madhavan, Kahini Wadhawan
We study attribute control in language models through the method of Causal Average Treatment Effect (Causal ATE). Existing methods for the attribute control task in Language Models…
CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation
Rahul Madhavan, Rishabh Garg, Kahini Wadhawan +1
We propose a method to control the attributes of Language Models (LMs) for the text generation task using Causal Average Treatment Effect (ATE) scores and counterfactual augmentati…
Attribute Graphs Underlying Molecular Generative Models: Path to Learning with Limited Data
Samuel C. Hoffman, Payel Das, Karthikeyan Shanmugam +2
Training generative models that capture rich semantics of the data and interpreting the latent representations encoded by such models are very important problems in un-/self-superv…
Towards Interpreting Zoonotic Potential of Betacoronavirus Sequences With Attention
Kahini Wadhawan, Payel Das, Barbara A. Han +4
Current methods for viral discovery target evolutionarily conserved proteins that accurately identify virus families but remain unable to distinguish the zoonotic potential of newl…
Optimizing Molecules using Efficient Queries from Property Evaluations
Samuel Hoffman, Vijil Chenthamarakshan, Kahini Wadhawan +2
Machine learning based methods have shown potential for optimizing existing molecules with more desirable properties, a critical step towards accelerating new chemical discovery. H…
Effects of Naturalistic Variation in Goal-Oriented Dialog
Jatin Ganhotra, Robert Moore, Sachindra Joshi +1
Existing benchmarks used to evaluate the performance of end-to-end neural dialog systems lack a key component: natural variation present in human conversations. Most datasets are c…
Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics
Payel Das, Tom Sercu, Kahini Wadhawan +12
De novo therapeutic design is challenged by a vast chemical repertoire and multiple constraints, e.g., high broad-spectrum potency and low toxicity. We propose CLaSS (Controlled La…
Co-regularized Alignment for Unsupervised Domain Adaptation
Abhishek Kumar, Prasanna Sattigeri, Kahini Wadhawan +4
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from t…
PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences
Payel Das, Kahini Wadhawan, Oscar Chang +6
Given the emerging global threat of antimicrobial resistance, new methods for next-generation antimicrobial design are urgently needed. We report a peptide generation framework Pep…
Improved Neural Text Attribute Transfer with Non-parallel Data
Igor Melnyk, Cicero Nogueira dos Santos, Kahini Wadhawan +2
Text attribute transfer using non-parallel data requires methods that can perform disentanglement of content and linguistic attributes. In this work, we propose multiple improvemen…
Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks
Cicero Nogueira dos Santos, Kahini Wadhawan, Bowen Zhou
We propose discriminative adversarial networks (DAN) for semi-supervised learning and loss function learning. Our DAN approach builds upon generative adversarial networks (GANs) an…