A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges
Dynamic Graph Neural Networks (GNNs) combine temporal information with GNNs to
capture structural, temporal, and contextual relationships in dynamic graphs simultaneously …
capture structural, temporal, and contextual relationships in dynamic graphs simultaneously …
TCGC: Temporal Collaboration-Aware Graph Co-Evolution Learning for Dynamic Recommendation
Dynamic recommendation systems, where users interact with items continuously over time,
have been widely deployed in real-world online streaming applications. The burst of …
have been widely deployed in real-world online streaming applications. The burst of …
Union subgraph neural networks
Graph Neural Networks (GNNs) are widely used for graph representation learning in many
application domains. The expressiveness of vanilla GNNs is upper-bounded by 1 …
application domains. The expressiveness of vanilla GNNs is upper-bounded by 1 …
[PDF][PDF] TimeSGN: Scalable and Effective Temporal Graph Neural Network
Temporal graph neural networks (T-GNNs) have emerged as leading approaches for
representation learning over dynamic graphs. However, existing solutions typically suffer …
representation learning over dynamic graphs. However, existing solutions typically suffer …
Benchmarking Edge Regression on Temporal Networks
Benchmark datasets and task definitions in temporal graph learning are limited to dynamic
node classification and future link prediction. In this paper, we consider the task of edge …
node classification and future link prediction. In this paper, we consider the task of edge …
Ranking on Dynamic Graphs: An Effective and Robust Band-Pass Disentangled Approach
Y Li, Y Xu, X Lin, W Zhang, Y Zhang - THE WEB CONFERENCE 2025 - openreview.net
Ranking is an essential and practical task on dynamic graphs, which aims to prioritize future
interaction candidates for given queries. While existing solutions achieve promising ranking …
interaction candidates for given queries. While existing solutions achieve promising ranking …