Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Towards Unsupervised Deep Graph Structure Learning

About

In recent years, graph neural networks (GNNs) have emerged as a successful tool in a variety of graph-related applications. However, the performance of GNNs can be deteriorated when noisy connections occur in the original graph structures; besides, the dependence on explicit structures prevents GNNs from being applied to general unstructured scenarios. To address these issues, recently emerged deep graph structure learning (GSL) methods propose to jointly optimize the graph structure along with GNN under the supervision of a node classification task. Nonetheless, these methods focus on a supervised learning scenario, which leads to several problems, i.e., the reliance on labels, the bias of edge distribution, and the limitation on application tasks. In this paper, we propose a more practical GSL paradigm, unsupervised graph structure learning, where the learned graph topology is optimized by data itself without any external guidance (i.e., labels). To solve the unsupervised GSL problem, we propose a novel StrUcture Bootstrapping contrastive LearnIng fraMEwork (SUBLIME for abbreviation) with the aid of self-supervised contrastive learning. Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph. To provide persistent guidance, we design a novel bootstrapping mechanism that upgrades the anchor graph with learned structures during model learning. We also design a series of graph learners and post-processing schemes to model the structures to learn. Extensive experiments on eight benchmark datasets demonstrate the significant effectiveness of our proposed SUBLIME and high quality of the optimized graphs.

Yixin Liu, Yu Zheng, Daokun Zhang, Hongxu Chen, Hao Peng, Shirui Pan• 2022

Related benchmarks

TaskDatasetResultRank
Node ClassificationCora
Accuracy82.35
583
Node ClassificationPubmed
Accuracy80.2
363
Node ClassificationRoman-Empire
Accuracy64.59
327
Node ClassificationOgbn-arxiv
Accuracy70.24
235
Node ClassificationCiteseer
Mean Accuracy72.6
202
Node ClassificationCiteseer
Accuracy (%)73.12
105
Node-level classificationBlogCatalog
Accuracy0.9478
70
Node ClassificationACM
Accuracy91.81
47
Node ClassificationYelp
Accuracy90.91
35
Node ClassificationDBLP
Accuracy91.49
31
Showing 10 of 26 rows

Other info

Follow for update