activity
20132023
most citedA Theoretical Analysis of NDCG Type Ranking Measures

253 citations · 733 across the 28 of their papers we have counts for

collaborators
Showing cs.LGShow all

21 papers · 1 filter

cs.LG2023

CORE: Common Random Reconstruction for Distributed Optimization with Provable Low Communication Complexity

Pengyun Yue, Hanzhen Zhao, Cong Fang +4

With distributed machine learning being a prominent technique for large-scale machine learning tasks, communication complexity has become a major bottleneck for speeding up trainin…

cs.LG2023★ 25 cited

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…

cs.LG2023★ 2 cited

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…

cs.LG2023★ 2 cited

Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers

Krzysztof Marcin Choromanski, Shanda Li, Valerii Likhosherstov +7

We propose a new class of linear Transformers called FourierLearner-Transformers (FLTs), which incorporate a wide range of relative positional encoding mechanisms (RPEs). These inc…

cs.LG2023★ 15 cited

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…

cs.LG2022★ 12 cited

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…