Abstract
In recent years, graph neural networks (GNNs) have emerged as a potent tool for learning on graph-structured data and won fruitful successes in varied fields. The majority of GNNs follow the message-passing paradigm, where representations of each node are learned by recursively aggregating features of its neighbors. However, this mechanism brings severe over-smoothing and efficiency issues over high-degree graphs (HDGs), wherein most nodes have dozens (or even hundreds) of neighbors, such as social networks, transaction graphs, power grids, etc. Additionally, such graphs usually encompass rich and complex structure semantics, which are hard to capture merely by feature aggregations in GNNs.
Motivated by the above limitations, we propose TADA, an efficient and effective front-mounted data augmentation framework for GNNs on HDGs. Under the hood, TADA includes two key modules: (i) feature expansion with structure embeddings, and (ii) topology- and attribute-aware graph sparsification. The former obtains augmented node features and enhanced model capacity by encoding the graph structure into high-quality structure embeddings with our highly-efficient sketching method. Further, by exploiting task-relevant features extracted from graph structures and attributes, the second module enables the accurate identification and reduction of numerous redundant/noisy edges from the input graph, thereby alleviating over-smoothing and facilitating faster feature aggregations over HDGs. Empirically, \algo considerably improves the predictive performance of mainstream GNN models on 8 real homophilic/heterophilic HDGs in terms of node classification, while achieving efficient training and inference processes.
Motivated by the above limitations, we propose TADA, an efficient and effective front-mounted data augmentation framework for GNNs on HDGs. Under the hood, TADA includes two key modules: (i) feature expansion with structure embeddings, and (ii) topology- and attribute-aware graph sparsification. The former obtains augmented node features and enhanced model capacity by encoding the graph structure into high-quality structure embeddings with our highly-efficient sketching method. Further, by exploiting task-relevant features extracted from graph structures and attributes, the second module enables the accurate identification and reduction of numerous redundant/noisy edges from the input graph, thereby alleviating over-smoothing and facilitating faster feature aggregations over HDGs. Empirically, \algo considerably improves the predictive performance of mainstream GNN models on 8 real homophilic/heterophilic HDGs in terms of node classification, while achieving efficient training and inference processes.
Original language | English |
---|---|
Title of host publication | KDD 2024 - Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining |
Publisher | Association for Computing Machinery (ACM) |
Pages | 1463-1473 |
Number of pages | 11 |
ISBN (Electronic) | 9798400704901 |
DOIs | |
Publication status | Published - 24 Aug 2024 |
Event | 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024 - Barcelona, Spain Duration: 25 Aug 2024 → 29 Aug 2024 https://kdd2024.kdd.org/ |
Publication series
Name | Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining |
---|---|
ISSN (Print) | 2154-817X |
Conference
Conference | 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024 |
---|---|
Country/Territory | Spain |
City | Barcelona |
Period | 25/08/24 → 29/08/24 |
Internet address |
Scopus Subject Areas
- Software
- Information Systems
User-Defined Keywords
- data augmentation
- graph neural networks
- sketching
- sparsification