1 citations · 1 across the 11 of their papers we have counts for
11 papers
The Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifiers
Owais Makroo, Siva Rajesh Kasa, Sumegh Roychowdhury +4
Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a model's training dataset. Despit…
Generative or Discriminative? Revisiting Text Classification in the Era of Transformers
Siva Rajesh Kasa, Karan Gupta, Sumegh Roychowdhury +7
The comparison between discriminative and generative classifiers has intrigued researchers since Efron's seminal analysis of logistic regression versus discriminant analysis. While…
Exploring Ordinality in Text Classification: A Comparative Study of Explicit and Implicit Techniques
Siva Rajesh Kasa, Aniket Goel, Karan Gupta +4
Ordinal Classification (OC) is a widely encountered challenge in Natural Language Processing (NLP), with applications in various domains such as sentiment analysis, rating predicti…
How Robust are LLMs to In-Context Majority Label Bias?
Karan Gupta, Sumegh Roychowdhury, Siva Rajesh Kasa +4
In the In-Context Learning (ICL) setup, various forms of label biases can manifest. One such manifestation is majority label bias, which arises when the distribution of labeled exa…
Tackling Concept Shift in Text Classification using Entailment-style Modeling
Sumegh Roychowdhury, Karan Gupta, Siva Rajesh Kasa +2
Pre-trained language models (PLMs) have seen tremendous success in text classification (TC) problems in the context of Natural Language Processing (NLP). In many real-world text cl…
CRUSH: Contextually Regularized and User anchored Self-supervised Hate speech Detection
Souvic Chakraborty, Parag Dutta, Sumegh Roychowdhury +1
The last decade has witnessed a surge in the interaction of people through social networking platforms. While there are several positive aspects of these social platforms, the prol…
Representation Learning for Conversational Data using Discourse Mutual Information Maximization
Bishal Santra, Sumegh Roychowdhury, Aishik Mandal +4
Although many pretrained models exist for text or images, there have been relatively fewer attempts to train representations specifically for dialog understanding. Prior works usua…
Video2Skill: Adapting Events in Demonstration Videos to Skills in an Environment using Cyclic MDP Homomorphisms
Sumedh A Sontakke, Sumegh Roychowdhury, Mausoom Sarkar +3
Humans excel at learning long-horizon tasks from demonstrations augmented with textual commentary, as evidenced by the burgeoning popularity of tutorial videos online. Intuitively,…
Leveraging Post Hoc Context for Faster Learning in Bandit Settings with Applications in Robot-Assisted Feeding
Ethan K. Gordon, Sumegh Roychowdhury, Tapomayukh Bhattacharjee +2
Autonomous robot-assisted feeding requires the ability to acquire a wide variety of food items. However, it is impossible for such a system to be trained on all types of food in ex…
SHERLock: Self-Supervised Hierarchical Event Representation Learning
Sumegh Roychowdhury, Sumedh A. Sontakke, Nikaash Puri +5
Temporal event representations are an essential aspect of learning among humans. They allow for succinct encoding of the experiences we have through a variety of sensory inputs. Al…
Exploring Effects of Random Walk Based Minibatch Selection Policy on Knowledge Graph Completion
Bishal Santra, Prakhar Sharma, Sumegh Roychowdhury +1
In this paper, we have explored the effects of different minibatch sampling techniques in Knowledge Graph Completion. Knowledge Graph Completion (KGC) or Link Prediction is the tas…