Puja Trivedi

I am a CSE PhD candidate in the Graph Exploration and Mining at Scale (GEMS) Lab at the University of Michigan, where I am fortunate to be advised by Prof. Danai Koutra. I also often collaborate with Dr. Jay Thiagarajan at Lawrence Livermore National Laboratory.

I am broadly interested in understanding how self-supervised learning can be performed effectively and reliably for non-euclidean and graph data by incorporating domain invariances and designing grounded algorithms. My recent work has focused on understanding the role of data augmentations in graph contrastive learning.

Email  /  CV  /  Google Scholar

profile photo
News
[06/2024] Completed thesis proposal. Defense planned for Fall 2024! Currently seeking full-time opportunities.
[01/2024] Our work on graph neural network uncertainty estimation was accepted at ICLR!
[12/2023] Our work on calibrating GNNs when performing link prediction was accepted at ICASSP!
[10/2023] Started interning with Amazon Search in Palo Alto!
Selected Publications
gclr Large Language Model Guided Graph Clustering
Puja Trivedi, Nurendra Choudhary, Eddie Huang, Vasileios Ioannidis, Karthik Subbian, Danai Koutra
Preprint, 2024
bibtex / Paper

We introduce GCLR, an active-learning framework for improving gnn-based graph clustering with LLM guidance.

gduq Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
Puja Trivedi, Mark Heimann, Rushil Anirudh, Danai Koutra, Jay J. Thiagarajan
International Conference on Learning Representations (ICLR), 2024
bibtex / arXiv / Code / Project Page

We introduce G-ΔUQ, an accurate and scalable strategy for obtaining reliable uncertainty estimates for node classification and graph classification tasks.

closerlook A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
Puja Trivedi, Danai Koutra, Jay J. Thiagarajan
International Conference on Learning Representations (ICLR), 2023 (Spotlight)
bibtex / arXiv / Code

We study how adaptation protocols can induce safe and effective generalization on downstream tasks through the lens of feature distortion and simplicity bias.

scoringfuncs On the Efficacy of Generalization Error Prediction Scoring Functions
Puja Trivedi, Danai Koutra, Jay J. Thiagarajan
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023
bibtex / arXiv / Code

We rigorously study the effectiveness of popular scoring functions under distribution shifts and corruptions

datacentricsssl Analyzing Data-Centric Properties for Contrastive Learning on Graphs
Puja Trivedi, Ekdeep Singh Lubana, Mark Heimann, Danai Koutra, and Jay J. Thiagarajan
Advances in Neural Information Processing Systems (NeurIPS), 2022
bibtex / arXiv / Code

We provide a novel generalization analysis for graph contrastive learning with popularly used, generic graph augmentations. Our analysis identifies several limitations in current self-supervised graph learning practices.

www Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices
Puja Trivedi, Ekdeep Singh Lubana, Yujun Yan, Yaoqing Yang, and Danai Koutra
ACM The Web Conference (formerly WWW), 2022
bibtex / arXiv / Code

We contextualize the performance of several unsupervised graph representation learning methods with respect to inductive bias of GNNs and show significant improvements by using structured augmentations defined by task-relevance.


Website Design from: here.