Towards adaptive neighborhood for advancing temporal interaction graph modeling
Temporal Graph Networks (TGNs) have demonstrated their remarkable performance in
modeling temporal interaction graphs. These works can generate temporal node …
modeling temporal interaction graphs. These works can generate temporal node …
Prompt learning on temporal interaction graphs
Temporal Interaction Graphs (TIGs) are widely utilized to represent real-world systems. To
facilitate representation learning on TIGs, researchers have proposed a series of TIG …
facilitate representation learning on TIGs, researchers have proposed a series of TIG …
Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting
Recent years have witnessed great success in handling graph-related tasks with graph
neural networks (GNNs). However, most existing GNNs are based on message passing to …
neural networks (GNNs). However, most existing GNNs are based on message passing to …
DTFormer: A Transformer-Based Method for Discrete-Time Dynamic Graph Representation Learning
Discrete-Time Dynamic Graphs (DTDGs), which are prevalent in real-world implementations
and notable for their ease of data acquisition, have garnered considerable attention from …
and notable for their ease of data acquisition, have garnered considerable attention from …
Robust Sequence-Based Self-Supervised Representation Learning for Anti-Money Laundering
S Huang, Y **ong, Y **e, T Qiu, G Wang - Proceedings of the 33rd ACM …, 2024 - dl.acm.org
As online transactions rapidly increase, money laundering has become more difficult to
detect, rendering traditional rule-based algorithms inadequate for the current severe …
detect, rendering traditional rule-based algorithms inadequate for the current severe …
DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning
We investigate the replay buffer in rehearsal-based approaches for graph continual learning
(GCL) methods. Existing rehearsal-based GCL methods select the most representative …
(GCL) methods. Existing rehearsal-based GCL methods select the most representative …
DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models
Dynamic graphs exhibit intertwined spatio-temporal evolutionary patterns, widely existing in
the real world. Nevertheless, the structure incompleteness, noise, and redundancy result in …
the real world. Nevertheless, the structure incompleteness, noise, and redundancy result in …
Multi-view Graph Structural Representation Learning via Graph Coarsening
Graph Transformers (GTs) have made remarkable achievements in graph-level tasks.
However, most existing works regard graph structures as a form of guidance or bias for …
However, most existing works regard graph structures as a form of guidance or bias for …
Adaptive Spatiotemporal Augmentation for Improving Dynamic Graph Learning
X Chu, H Xue, B Wang, X Liu, W Li, T Mo… - arxiv preprint arxiv …, 2025 - arxiv.org
Dynamic graph augmentation is used to improve the performance of dynamic GNNs. Most
methods assume temporal locality, meaning that recent edges are more influential than …
methods assume temporal locality, meaning that recent edges are more influential than …
GSL-Mash: Enhancing Mashup Creation Service Recommendations Through Graph Structure Learning
Abstract The proliferation of Web APIs has facilitated the creation of numerous software
applications through the integration of diverse services, commonly referred to as mashups …
applications through the integration of diverse services, commonly referred to as mashups …