.png){kind=icon}
.png){kind=icon}
返回
Unsupervised Graph Representation Learning Beyond Aggregated View
.png){kind=icon}
PRE
AI
DOI：10.1109/TKDE.2024.3418576.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Unsupervised graph representation learning aims to condense graph information into dense vector embeddings to support various downstream tasks. To achieve this goal, existing UGRL approaches mainly adopt the message-passing mechanism to simultaneously incorporate graph topology and node attribute with an aggregated view. However, recent research points out that this direct aggregation may lead to issues such as over-smoothing and/or topology distortion, as topology and node attribute of totally different semantics. To address this issue, this paper proposes a novel Graph Dual-view AutoEncoder framework (GDAE) which introduces the node-wise view for an individual node beyond the traditional aggregated view for aggregation of connected nodes. Specifically, the node-wise view captures the unique characteristics of individual node through a decoupling design, i.e., topology encoding by multi-steps random walk while preserving node-wise individual attribute. Meanwhile, the aggregated view aims to better capture the collective commonality among long-range nodes through an enhanced strategy, i.e., topology masking then attribute aggregation. Extensive experiments on 5 synthetic and 11 real-world benchmark datasets demonstrate that GDAE achieves the best results with up to 49.5% and 21.4% relative improvement in node degree prediction and cut-vertex detection tasks and remains top in node classification and link prediction tasks.
Keyword:
Topology
Encoding
Network topology
Decoding
Data mining
Synthetic data
Benchmark testing
Graph representation learning
self-supervised
topology and attribute features
dual-view autoencoder
期刊
IF:
10.4
论文数:
6.8K
被引数:
3.2W