cs.LGNov 18, 2026

DyNA-Mixer: Decoupling Time and Topology for Scalable Dynamic Node Affinity Prediction

Authors: Yuanxing Zheng, Liping Wang, Xuemin Lin

Organizations: East China Normal University, Shanghai, China · Shanghai Jiao Tong University, Shanghai, China

Abstract

Continuous-time dynamic graphs preserve the ordering, timing, and evolving strength of interactions that static snapshots discard, making dynamic graph mining essential for evolving systems such as recommender systems, trade networks, and transaction platforms. Research in this area has centered on dynamic link prediction, which forecasts only whether a future interaction will occur, whereas many applications also need its intensity. The dynamic node affinity prediction (DNAP) problem generalizes this task to continuous targets and full-candidate ranking, making it more broadly applicable but substantially harder. This raises two coupled difficulties: ranking requires a predictor expressive enough to capture both multi-scale temporal evolution and graph-wide collaborative patterns, yet running such a predictor over every source--destination pair is computationally prohibitive. We propose DyNA-Mixer, which decouples temporal forecasting from collaborative structure modeling. It adopts a multi-scale temporal predictor for pair-specific affinity evolution, constructs a Virtual Collaborative Graph that infers query-time relationships and aggregates trends from related interactions, and fuses the two through a gated residual mechanism. A sparsity-aware evaluation strategy further restricts expensive forecasting to pairs with recent non-zero affinities. Experiments on four Temporal Graph Benchmark datasets for the DNAP problem show that DyNA-Mixer achieves new state-of-the-art NDCG@10 on every dataset, including a 17.8% relative test improvement over the strongest baseline on tgbn-token, the largest dataset.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. A Common Language for Dynamic Graphs: Interaction Tokenization Enables Foundation Models

    Nov 2, 2026Fuyuan Ma, Yili Wang, Xin He +3Graph Foundation ModelsTemporal Link Prediction

  2. Dynamic Graph with Similarity-Aware Attention Graph Neural Network for Recommender Systems

    May 2, 2026Aadarsh Senapati, Neha Kujur, Vivek YelletiDynamic Graph LearningRecommender Systems

  3. CacheDyG: Decoupling Temporal Propagation for Efficient Dynamic Graph Learning

    Sep 22, 2026PinHeng Zong, Ye YuanTemporal GNNsTemporal Link Prediction