Pith. sign in

REVIEW 12 cited by

Inductive Representation Learning on Temporal Graphs

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2002.07962 v1 pith:WGNTUK55 submitted 2020-02-19 cs.LG stat.ML

Da Xu , Chuanwei Ruan , Evren Korpeoglu , Sushant Kumar , Kannan Achan This is my paper
classification cs.LGstat.ML
keywords temporalnodeembeddingsfeaturestgatwellgraphgraphs
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both the static node features and the evolving topological structures. Moreover, node and topological features can be temporal as well, whose patterns the node embeddings should also capture. We propose the temporal graph attention (TGAT) layer to efficiently aggregate temporal-topological neighborhood features as well as to learn the time-feature interactions. For TGAT, we use the self-attention mechanism as building block and develop a novel functional time encoding technique based on the classical Bochner's theorem from harmonic analysis. By stacking TGAT layers, the network recognizes the node embeddings as functions of time and is able to inductively infer embeddings for both new and observed nodes as the graph evolves. The proposed approach handles both node classification and link prediction task, and can be naturally extended to include the temporal edge features. We evaluate our method with transductive and inductive tasks under temporal settings with two benchmark and one industrial dataset. Our TGAT model compares favorably to state-of-the-art baselines as well as the previous temporal graph embedding approaches.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

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

  1. UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure

    cs.CL 2026-05 conditional novelty 6.0 of 10

    UniSAGE jointly models static and dynamic attributes in a single attribute graph and improves entity classification/regression over prior RDL and GNN baselines.

  2. 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.

  3. CoBAD: Modeling Collective Behaviors for Human Mobility Anomaly Detection

    cs.LG 2025-08 conditional novelty 6.0 of 10

    CoBAD detects collective mobility anomalies (unexpected co-occurrence and absence) by pre-training a two-stage attention model over collective event sequences and event graphs.

  4. 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.

  5. Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs

    cs.LG 2026-07 conditional novelty 5.0 of 10

    SG-JEPA applies joint-embedding predictive learning to dynamic graphs, using spiking-neuron context encoders to predict future node embeddings without edge reconstruction or graph augmentation.

  6. A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction

    quant-ph 2026-05 unverdicted novelty 5.0 of 10

    A hybrid quantum-classical temporal graph network with adaptive amplitude encoding claims strong link-prediction results on five TGBL benchmarks, but the evaluation is undermined by a below-random baseline and missing code.

  7. TCAR-Gen: Temporal Graph Retrieval with Evidence Fusion for Knowledge-Grounded Generation

    cs.CL 2026-04 conditional novelty 5.0 of 10

    A query-conditioned temporal graph RAG with chain-of-trees fusion reaches 0.3738 Recall@5 on a Victorian crime diaries QA set, beating standard and graph RAG baselines.

  8. DiT-SGCR: Directed Temporal Structural Representation with Global-Cluster Awareness for Ethereum Malicious Account Detection

    cs.CE 2025-06 reject novelty 5.0 of 10

    DiT-SGCR claims to improve Ethereum malicious account detection by 3.62% to 10.83% F1 over state-of-the-art via directed temporal clustering embeddings, but the supporting experiments and algorithm formulation have cr...

  9. GTIN: A Unified Framework for Joint Event and Time Prediction in Temporal Graphs

    cs.SI 2026-07 conditional novelty 4.0 of 10

    An edge-centric message-passing model jointly scores next-event location, Gaussian time, and features from a global temporal graph embedding and beats listed baselines on time RMSE.

  10. Non-exchangeable Conformal Prediction for Temporal Graph Neural Networks

    cs.LG 2025-07 reject novelty 4.0 of 10

    NCPNet applies non-exchangeable conformal prediction to temporal graphs by diffusing non-conformity scores over graph and time neighbors and learning weighted quantiles to reduce prediction set size.

  11. A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams

    cs.LG 2025-06 reject novelty 4.0 of 10

    BADGNN adds a Lipschitz regularizer and an attention-temperature adjustment so that memory-based dynamic GNNs can train with large batches while keeping predictive accuracy.

  12. SEP-GCN: Leveraging Similar Edge Pairs with Temporal and Spatial Contexts for Location-Based Recommender Systems

    cs.IR 2025-06 conditional novelty 4.0 of 10

    SEP-GCN augments a LightGCN recommender with edges between check-ins that share time slots and nearby locations, and reports consistent gains over baselines on NYC, Gowalla, and Brightkite.

Pith tools