GTEA: Inductive Representation Learning on Temporal Interaction Graphs via Temporal Edge Aggregation
Refereed conference paper presented and published in conference proceedings

Altmetrics Information

Other information
AbstractIn this paper, we propose the Graph Temporal Edge Aggregation (GTEA) framework for inductive learning on Temporal Interaction Graphs (TIGs). Different from previous works, GTEA models the temporal dynamics of interaction sequences in the continuous-time space and simultaneously takes advantage of both rich node and edge/ interaction attributes in the graph. Concretely, we integrate a sequence model with a time encoder to learn pairwise interactional dynamics between two adjacent nodes. This helps capture complex temporal interactional patterns of a node pair along the history, which generates edge embeddings that can be fed into a GNN backbone. By aggregating features of neighboring nodes and the corresponding edge embeddings, GTEA jointly learns both topological and temporal dependencies of a TIG. In addition, a sparsity-inducing self-attention scheme is incorporated for neighbor aggregation, which highlights more important neighbors and suppresses trivial noises for GTEA. By jointly optimizing the sequence model and the GNN backbone, GTEA learns more comprehensive node representations capturing both temporal and graph structural characteristics. Extensive experiments on five large-scale real-world datasets demonstrate the superiority of GTEA over other inductive models.
Acceptance Date22/02/2023
All Author(s) ListSiyue Xie, Yiming Li, Da Sun Handason Tam, Xiaxin Liu, Qiufang Ying, Wing Cheong Lau, Dah Ming Chiu, Shouzhi Chen
Name of Conference27th Pacific-Asia Conference on Knowledge Discovery and Data Mining
Start Date of Conference25/05/2023
End Date of Conference28/05/2023
Place of ConferenceOsaka
Country/Region of ConferenceJapan
Proceedings Title27th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2023, Proceedings, Part II
Volume Number13936
Pages28 - 39
LanguagesEnglish-United States
KeywordsEdge Embedding, Graph Neural Networks, Self-attention, Temporal Dynamics Modeling, Temporal Interaction Graphs

Last updated on 2023-29-10 at 03:08