10 citations · 17 across the 10 of their papers we have counts for
7 papers · 1 filter
MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data
Jiaqi Sun, Boyang Sun, Rasmy M. H. +2
Continual learning requires models to adapt to new data while preserving previously acquired knowledge. At its core, this challenge can be viewed as principled one-step adaptation:…
SEDGE: Structural Extrapolated Data Generation
Kun Zhang, Jiaqi Sun, Yiqing Li +3
This paper aims to address the challenge of data generation beyond the training data and proposes a framework for Structural Extrapolated Data GEneration (SEDGE) based on suitable…
MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification
Tianjun Yao, Jiaqi Sun, Defu Cao +2
Recent works have introduced GNN-to-MLP knowledge distillation (KD) frameworks to combine both GNN's superior performance and MLP's fast inference speed. However, existing KD frame…
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
Peng Xu, Lin Zhang, Xuanzhou Liu +4
Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these me…
D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching
Xuanzhou Liu, Lin Zhang, Jiaqi Sun +2
Subgraph matching is a fundamental building block for graph-based applications and is challenging due to its high-order combinatorial nature. Existing studies usually tackle it by…
Feature Expansion for Graph Neural Networks
Jiaqi Sun, Lin Zhang, Guangyi Chen +3
Graph neural networks aim to learn representations for graph-structured data and show impressive performance, particularly in node classification. Recently, many methods have studi…
Improving Your Graph Neural Networks: A High-Frequency Booster
Jiaqi Sun, Lin Zhang, Shenglin Zhao +1
Graph neural networks (GNNs) hold the promise of learning efficient representations of graph-structured data, and one of its most important applications is semi-supervised node cla…