25 citations · 80 across the 12 of their papers we have counts for
12 papers
Homomorphism Expressivity of Spectral Invariant Graph Neural Networks
Jingchu Gai, Yiheng Du, Bohang Zhang +2
Graph spectra are an important class of structural features on graphs that have shown promising results in enhancing Graph Neural Networks (GNNs). Despite their widespread practica…
On the Expressive Power of Spectral Invariant Graph Neural Networks
Bohang Zhang, Lingxiao Zhao, Haggai Maron
Incorporating spectral information to enhance Graph Neural Networks (GNNs) has shown promising results but raises a fundamental challenge due to the inherent ambiguity of eigenvect…
Do Efficient Transformers Really Save Computation?
Kai Yang, Jan Ackermann, Zhenyu He +6
As transformer-based language models are trained on increasingly large datasets and with vast numbers of parameters, finding more efficient alternatives to the standard Transformer…
Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
Bohang Zhang, Jingchu Gai, Yiheng Du +3
Designing expressive Graph Neural Networks (GNNs) is a fundamental topic in the graph learning community. So far, GNN expressiveness has been primarily assessed via the Weisfeiler-…
Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective
Guhao Feng, Bohang Zhang, Yuntian Gu +3
Recent studies have discovered that Chain-of-Thought prompting (CoT) can dramatically improve the performance of Large Language Models (LLMs), particularly when dealing with comple…
A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests
Bohang Zhang, Guhao Feng, Yiheng Du +2
Recently, subgraph GNNs have emerged as an important direction for developing expressive graph neural networks (GNNs). While numerous architectures have been proposed, so far there…
Rethinking the Expressive Power of GNNs via Graph Biconnectivity
Bohang Zhang, Shengjie Luo, Liwei Wang +1
Designing expressive Graph Neural Networks (GNNs) is a central topic in learning graph-structured data. While numerous approaches have been proposed to improve GNNs in terms of the…
Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective
Bohang Zhang, Du Jiang, Di He +1
Designing neural networks with bounded Lipschitz constant is a promising way to obtain certifiably robust classifiers against adversarial examples. However, the relevant progress f…
Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis
Jikai Jin, Bohang Zhang, Haiyang Wang +1
Distributionally robust optimization (DRO) is a widely-used approach to learn models that are robust against distribution shift. Compared with the standard optimization setting, th…
Boosting the Certified Robustness of L-infinity Distance Nets
Bohang Zhang, Du Jiang, Di He +1
Recently, Zhang et al. (2021) developed a new neural network architecture based on -distance functions, which naturally possesses certified robustness by…
Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons
Bohang Zhang, Tianle Cai, Zhou Lu +2
It is well-known that standard neural networks, even with a high classification accuracy, are vulnerable to small -norm bounded adversarial perturbations. Although man…
Improved Analysis of Clipping Algorithms for Non-convex Optimization
Bohang Zhang, Jikai Jin, Cong Fang +1
Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, \citet{zhang2019gradient…