VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections

no code implementations • 24 Mar 2024 • Dongqi Fu, Zhigang Hua, Yan Xie, Jin Fang, Si Zhang, Kaan Sancak, Hao Wu, Andrey Malevich, Jingrui He, Bo Long

Therefore, mini-batch training for graph transformers is a promising direction, but limited samples in each mini-batch can not support effective dense attention to encode informative representations.

Feature Engineering Graph Learning

A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs

1 code implementation • NeurIPS 2021 • Runzhong Wang, Zhigang Hua, Gan Liu, Jiayi Zhang, Junchi Yan, Feng Qi, Shuang Yang, Jun Zhou, Xiaokang Yang

Combinatorial Optimization (CO) has been a long-standing challenging research topic featured by its NP-hard nature.

Combinatorial Optimization Scheduling

Learning to Schedule DAG Tasks

no code implementations • 5 Mar 2021 • Zhigang Hua, Feng Qi, Gan Liu, Shuang Yang

Scheduling computational tasks represented by directed acyclic graphs (DAGs) is challenging because of its complexity.

Scheduling

Variational Optimization for the Submodular Maximum Coverage Problem

no code implementations • 10 Jun 2020 • Jian Du, Zhigang Hua, Shuang Yang

We examine the \emph{submodular maximum coverage problem} (SMCP), which is related to a wide range of applications.

Solving Billion-Scale Knapsack Problems

no code implementations • 2 Feb 2020 • Xingwen Zhang, Feng Qi, Zhigang Hua, Shuang Yang

Knapsack problems (KPs) are common in industry, but solving KPs is known to be NP-hard and has been tractable only at a relatively small scale.

Distributed Computing