Kshiteesh Hegde

San Jose, CA

Previously, I was a member of the Core Analytics Team at Western Digital. Before that, I was part of Dr. Malik Magdon-Ismail’s Learning From Data Lab at Rensselaer where I got my PhD. I also have an MS in Computer Science from University of Minnesota.

Some of my research interests include recommender systems, LLMs, machine learning on social networks, object detection and segmentation using deep learning, and learning from tabular data. Feel free to reach out to me to talk about any of these topics or more!

_{^{Disclaimer: All opinions expressed here (and anywhere else) are solely my own.}}

news

Oct 21, 2024	I’m joining Pinterest as a Machine Learning Engineer!
Sep 21, 2024	I’ll be chairing the session Recommender Systems II at CIKM 2024!
Aug 16, 2024	Our paper on Causal Reasoning has been accepted to the AAAI Fall Symposium Series 2024!

selected publications

Cause and effect: Can large language models truly understand causality?

Swagata Ashwani, Kshiteesh Hegde, Nishith Reddy Mannuru, and 6 more authors

In Proceedings of the AAAI Symposium Series, 2024
The intrinsic scale of networks is small

Malik Magdon-Ismail, and Kshiteesh Hegde

In Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2019
Network Signatures from Image Representation of Adjacency Matrices: Deep/Transfer Learning for Subgraph Classification

Kshiteesh Hegde, Malik Magdon-Ismail, Ram Ramanathan, and 1 more author

2018
Recommendations For Streaming Data

Karthik Subbian, Charu Aggarwal, and Kshiteesh Hegde

In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, 2016

Abs

Recommender systems have become increasingly popular in recent years because of the broader popularity of many web-enabled electronic commerce applications. However, most recommender systems today are designed in the context of an offline setting. The online setting is, however, much more challenging because the existing methods do not work very effectively for very large-scale systems. In many applications, it is desirable to provide real-time recommendations in large-scale scenarios. The main problem in applying streaming algorithms for recommendations is that the in-core storage space for memory-resident operations is quite limited. In this paper, we present a probabilistic neighborhood-based algorithm for performing recommendations in real-time. We present experimental results, which show the effectiveness of our approach in comparison to state-of-the-art methods.