arrow
返回

Differential Encoding for Improved Representation Learning Over Graphs

delete2025-10-07
delete0
PRE
AI
H
Haimin Zhang
J
Jiahao Xia
M
Min Xu
DOI:10.1109/TBDATA.2025.3618447delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Combining the message-passing paradigm with the global attention mechanism has emerged as an effective framework for learning over graphs. The message-passing paradigm and the global attention mechanism basically generate embeddings of nodes by taking the sum of information from a node’s local neighbourhood and from the entire graph, respectively. However, this simple summation aggregation approach fails to distinguish between the information from a node itself or from the node’s neighbours. Therefore, there exists information lost at each layer of embedding generation, and this information lost could be accumulated and become more serious in deeper model layers. In this paper, we present a differential encoding method to address the issue of information lost. Instead of simply taking the sum to aggregate local or global information, we explicitly encode the difference between the information from a node itself and that from the node’s local neighbours (or from the rest of the entire graph nodes). The obtained differential encoding is then combined with the original aggregated representation to generate the updated node embedding. By combining differential encodings, the representational ability of generated node embeddings is improved, and therefore the model performance is improved. The differential encoding method is empirically evaluated on different graph tasks on seven benchmark datasets. The results show that it is a general method that improves the message-passing update and the global attention update, advancing the state-of-the-art performance for graph representation learning on these benchmark datasets.
Keyword:
Graph representation learning
differential representation encoding
feature aggregation

期刊

I
IEEE Transactions on Big Data
IF:
5.7
论文数:
860
被引数:
3.0K

机构

U
university of technology sydney
学者数:
1.6W
论文数: 2.0W
被引数: 25
引用论文

引用论文

Automatic Relation-aware Graph Network Proliferation
err2022-06-01
err0
errOAAI
errShaofei Cai; Liang Li; Xinzhe Han; Jiebo Luo; Zheng-Jun Zha; Qingming Huang
err分享
err收藏
Self-Consistent Graph Neural Networks for Semi-Supervised Node Classification
err2023-08-01
err1
PREAI
errLiu, Yanbei; Zhao, Shichuan; Wang, Xiao; Geng, Lei; Xiao, Zhitao; Lin, Jerry Chun-Wei
err分享
err收藏
err分享
err收藏
学者 查看更多内容