Pith. sign in

REVIEW 8 cited by

TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2105.07944 v1 pith:DQMSKPHX submitted 2021-05-17 cs.LG cs.AI

classification cs.LGcs.AI
keywords graphdynamiclearningmodeltransformercontrastiveinteractionrepresentations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Dynamic graph modeling has recently attracted much attention due to its extensive applications in many real-world scenarios, such as recommendation systems, financial transactions, and social networks. Although many works have been proposed for dynamic graph modeling in recent years, effective and scalable models are yet to be developed. In this paper, we propose a novel graph neural network approach, called TCL, which deals with the dynamically-evolving graph in a continuous-time fashion and enables effective dynamic node representation learning that captures both the temporal and topology information. Technically, our model contains three novel aspects. First, we generalize the vanilla Transformer to temporal graph learning scenarios and design a graph-topology-aware transformer. Secondly, on top of the proposed graph transformer, we introduce a two-stream encoder that separately extracts representations from temporal neighborhoods associated with the two interaction nodes and then utilizes a co-attentional transformer to model inter-dependencies at a semantic level. Lastly, we are inspired by the recently developed contrastive learning and propose to optimize our model by maximizing mutual information (MI) between the predictive representations of two future interaction nodes. Benefiting from this, our dynamic representations can preserve high-level (or global) semantics about interactions and thus is robust to noisy interactions. To the best of our knowledge, this is the first attempt to apply contrastive learning to representation learning on dynamic graphs. We evaluate our model on four benchmark datasets for interaction prediction and experiment results demonstrate the superiority of our model.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs

    cs.LG 2026-02 conditional novelty 6.0 of 10

    Role-disentangled Transformer plus temporal contrastive pretraining improves future edge classification with 10k labels on 7 of 8 DTGB datasets.

  2. What Do Temporal Graph Learning Models Learn?

    cs.LG 2025-10 conditional novelty 6.0 of 10

    Temporal graph models consistently learn to favor popular nodes but fail to learn edge direction, density, and recency.

  3. When Speed meets Accuracy: an Efficient and Effective Graph Model for Temporal Link Prediction

    cs.AI 2025-07 conditional novelty 6.0 of 10

    EAGLE predicts temporal links with top-k recent neighbors plus top-k shared temporal PageRank influencers, matching or beating transformer T-GNNs while running far faster.

  4. Learnable Spatial-Temporal Positional Encoding for Link Prediction

    cs.LG 2025-06 conditional novelty 6.0 of 10

    L-STEP learns time-evolving positional encodings for graph nodes via a learnable spectral filter and predicts links with MLPs only, matching or beating attention-based baselines on 13 temporal datasets.

  5. Future Link Prediction Without Memory or Aggregation

    cs.LG 2025-05 conditional novelty 6.0 of 10

    CRAFT replaces memory and aggregation with learnable node embeddings and destination-to-source-neighbor cross-attention, improving future link prediction on most of 17 temporal graph benchmarks.

  6. Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision

    cs.LG 2026-02 conditional novelty 5.0 of 10

    SDGAD combines residual event representations, a two-hypersphere restriction loss, and a normalizing-flow boundary to detect dynamic-graph anomalies with little or no supervision.

  7. Are We Really Measuring Progress? Transferring Insights from Evaluating Recommender Systems to Temporal Link Prediction

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Temporal link prediction benchmarks can rank models differently depending on sampling and aggregation choices, so current progress measurements are not reliable.

  8. Higher-order Structure Boosts Link Prediction on Temporal Graphs

    cs.LG 2025-05 reject novelty 5.0 of 10

    HTGN adds hyperedge memory and hypergraph convolution to temporal GNNs, claiming better dynamic link prediction and lower memory cost, but the reported results are undermined by data inconsistencies and invalid proofs.

Pith tools