English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

In 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 interactionsequences in the continuous-time space and simultaneously takes advantage ofboth rich node and edge/ interaction attributes in the graph. Concretely, weintegrate a sequence model with a time encoder to learn pairwise interactionaldynamics between two adjacent nodes.This helps capture complex temporalinteractional patterns of a node pair along the history, which generates edgeembeddings that can be fed into a GNN backbone. By aggregating features ofneighboring nodes and the corresponding edge embeddings, GTEA jointly learnsboth topological and temporal dependencies of a TIG. In addition, asparsity-inducing self-attention scheme is incorporated for neighboraggregation, which highlights more important neighbors and suppresses trivialnoises for GTEA. By jointly optimizing the sequence model and the GNN backbone,GTEA learns more comprehensive node representations capturing both temporal andgraph structural characteristics. Extensive experiments on five large-scalereal-world datasets demonstrate the superiority of GTEA over other inductivemodels.

GTEA: Inductive Representation Learning on Temporal Interaction Graphs via Temporal Edge Aggregation