CoChat
Sign Up
Cited by 0Advanced Graph Neural NetworksTopic ModelingRecommender Systems and Techniques

The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.

Rethinking Temporal Knowledge Graph Representation Learning: From Entities to Evolutionary Event-Centric Clusters

Open access
Chen, Qian, Chen, Ling·2026·Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1
DOI 10.1145/3770854.3780173
Open this paper in CoChat — free account

Abstract

Existing research on Temporal Knowledge Graph (TKG) representation learning focuses on decomposing events into entities and relations, then employing various approaches to learn entity and relation representations in a low-dimensional vector space. However, all existing research overlooks the correlations among events, even though events are the core constituent elements of TKGs and involve heterogeneous correlations. To this end, we propose a Heterogeneous evolutionary Event cluster Aware Representation learning approach in Temporal Knowledge Graphs (HEART), which is the first event-centric approach in TKGs. Specifically, a heterogeneous event graph construction module is proposed to capture the diverse pairwise correlations between events by building co-entity and proximity heterogeneous edges. In addition, an event-aware multi-step evolutionary clustering module is proposed to capture continuous high-order correlations among events at different timestamps. Furthermore, an event cluster-aware unsupervised alignment mechanism is proposed to preserve the temporal smoothness of event clusters through cross-temporal alignment. Moreover, an event cluster-based self-supervised optimization mechanism is proposed to optimize the representations of event clusters. Experimental results on seven real-world datasets demonstrate that HEART achieves the state-of-the-art performance, outperforming the runner-up by an average of 3.89%, 8.14%, 5.97%, and 6.92% in MRR, Hits@1, Hits@3, and Hits@10, respectively.

Overview

Integrity signals

Registry

Crossref · 10.1145/3770854.3780173

Cites

42 of 42 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Flagged first, then by citations

Show all 40 references

Research works printed but not linked: 7

  1. Elizabeth Boschee, Jennifer Lautenschlager, Sean O'Brien, Steve Shellman, James Starz, and Michael Ward. 2015. ICEWS coded event data. Harvard Dataverse, Vol. 12, 2 (2015).
  2. I-Ta Lee, Maria Leonor Pacheco, and Dan Goldwasser. 2020. Weakly-supervised modeling of contextualized event embedding for discourse relations. In Findings of the Association for Computational Linguistics: EMNLP. 4962-4972.
  3. Kalev Leetaru and Philip A Schrodt. 2013. GDELT: Global data on events, location, and tone, 1979-2012. In Proceedings of ISA Annual Convention, Vol. 2. 1-49.
  4. Farzaneh Mahdisoltani, Joanna Biega, and Fabian M Suchanek. 2013. YAGO3: A knowledge base from multilingual wikipedias. In Proceedings of Conference on Innovative Data Systems Research. 1-12.
  5. Rakshit Trivedi, Hanjun Dai, Yichen Wang, and Le Song. 2017. Know-Evolve: Deep temporal reasoning for dynamic knowledge graphs. In Proceedings of International Conference on Machine Learning. 3462-3471.
  6. Laurens van der Maaten and Geoffrey Hinton. 2021. Visualizing data using t-SNE. Journal of Machine Learning Research, Vol. 9, 11 (2021), 2579-2605.
  7. Michael D Ward, Andreas Beger, Josh Cutler, Matthew Dickenson, Cassy Dorff, and Ben Radford. 2013. Comparing GDELT and ICEWS event data. Analysis, Vol. 21, 1 (2013), 267-297.

Cited by

Still being checked.

Related

See all

Metadata

Authors
Chen, Q., & Chen, L.
Affiliations
Zhejiang University (CN)
ORCID
Venue
Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1
Publisher
ACM
Published
2026-04-20
Pages
82-93
DOI
10.1145/3770854.3780173
OpenAlex
W7171998772
Semantic Scholar
b6e21b06ff1a0fcbf1b56e7be9e4e730e95fddae
Cited by
0
References
40
FWCI
0.00
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion, cc-by)
Funders
the National Key Research and Development Program of China (2024YFB3312900)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
Keywords
temporal knowledge graphs, event clustering, self-supervised learning, temporal smoothness

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review