[ICLR 2022] "Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice" by Peihao Wang, Wenqing Zheng, Tianlong Chen, Zhangyang Wang

GraphCON (ICML 2022)

Gradient gating (ICLR 2023)

"Graph Convolutions Enrich the Self-Attention in Transformers!" NeurIPS 2024

[CVPR 2022] "The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy" by Tianlong Chen, Zhenyu Zhang, Yu Cheng, Ahmed Awadallah, Zhangyang Wang

[ICLR'25] "Understanding Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing" by Peihao Wang, Ruisi Cai, Yuehao Wang, Jiajun Zhu, Pragya Srivastava, Zhangyang Wang, Pan Li

A DGL implementation of "DeeperGCN: All You Need to Train Deeper GCNs".

Source code accompanying the paper "Reducing Over-smoothing in Graph Neural Networks Using Relational Embeddings" published in DLG-AAAI’23

ISI 7th Summer School Project on implementing 2-layer GCN on CORA, CiteSeer, PubMed datasets, using PyTorch, and analyzing Oversmoothing by going deep upto 1024 layers

Complete codebase and datasets for "revisiting oversmoothing in deep gcns"

[ICLR 2026] Oversmoothing, “Oversquashing”, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning

This project implements mechanisms to mitigate over-squashing, improving GNN performance on tasks requiring deep Networks.

In this work, we demonstrate that oversquashing is not limited to long-range tasks, but can also arise in short-range problems.

Exploring and visualizing limitations of message-passing paradigm for GNNs. 📉

Implementing node similarity measures into pytorch geometric

Supplementary code for paper 'GATE: How to Keep Out Intrusive Neighbors' to be published at ICML 2024