Soumya Sanyal

I am a Ph.D. student at the INK Lab, University of Southern California, working with Prof. Xiang Ren. Previously, I was a research assistant at the MALL Lab, Indian Institue of Science hosted by Prof. Partha Talukdar. Before IISc, I was a Senior Analyst at the Equities Risk Management team of Goldman Sachs, India. I completed my Bachelor's from the Indian Institute of Technology, Kharagpur in 2016.


I am broadly interested in Natural Language Processing and Deep Learning on Graphs. My recent research has focused on explanation-based learning and learning to reason with language models.

If you want to discuss more about my work, feel free to contact me at soumyasa [at] usc [dot] edu.


Google Scholar| Semantic Scholar| DBLP
Conference Publications

Discretized Integrated Gradients for Explaining Language Models
Soumya Sanyal*, Xiang Ren EMNLP 2021 | The 2021 Conference on Empirical Methods in Natural Language Processing
Paper| Code

A Re-evaluation of Knowledge Graph Completion Methods
Zhiqing Sun*, Shikhar Vashishth*, Soumya Sanyal*, Partha Talukdar, and Yiming Yang ACL 2020 | The 58th Annual Meeting of the Association for Computational Linguistics
Paper| Code

Composition-based Multi-Relational Graph Convolutional Networks
Soumya Sanyal*, Shikhar Vashishth*, Vikram Nitin, and Partha Talukdar ICLR-2020 | Eighth International Conference on Learning Representations
Paper| Code

InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions
Soumya Sanyal*, Shikhar Vashishth*, Vikram Nitin, Nilesh Agrawal, and Partha Talukdar AAAI-2020 | Thirty-Fourth AAAI Conference on Artificial Intelligence
Paper| Code

ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations
Ekagra Ranjan, Soumya Sanyal, and Partha Talukdar AAAI-2020 | Thirty-Fourth AAAI Conference on Artificial Intelligence
Paper| Code

Workshop Publications

SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning
Aaron Chan, Boyuan Long, Jiashu Xu, Soumya Sanyal, Tanishq Gupta, and Xiang Ren ICML Workshop | ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI
Paper| Code

MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Prediction
Soumya Sanyal, Janakiraman Balachandran, Naganand Yadati, Abhishek Kumar, Padmini Rajagopalan, Suchismita Sanyal, and Partha Talukdar NeurIPS Workshop | NeurIPS 2018 Workshop on Machine Learning for Molecules and Materials
Paper| Code


ProteinGCN: Protein model quality assessment using Graph Convolutional Networks
Soumya Sanyal, Ivan Anishchenko, Anirudh Dagar, David Baker, and Partha Talukdar Paper| Code


Reviewer:   AAAI 2021, NAACL 2021, DMKD
Sub-Reviewer:   EMNLP 2020, WWW 2020, ICML 2021, KDD 2021, TACL
© Copyright 2020 Soumya Sanyal.