aiqbench analysis
BridgeMem advances temporal knowledge graph forecasting by explicitly modeling pair-specific transition evidence through residual corrections, outperforming nine prior baselines across five benchmarks. This approach effectively bridges the gap between exact recurrence methods and learned attention estimators while leveraging backbone uncertainty to prevent overfitting on sparse data. The work demonstrates that capturing dyadic transition dynamics is critical for accurately predicting future relational facts in evolving knowledge graphs.
BridgeMem: Causal Dyadic Transition Residuals for Temporal Knowledge Graph Forecasting
arXiv:2609.29268v1 Announce Type: new Abstract: Temporal knowledge graph forecasting aims to infer future relational facts from the temporal structure of observed events. Existing forecasters mainly summarize history through entity states, relation states, paths, or exact recurrence. These views often miss pair-specific transition evidence, that is, the way prior relations between the query actor and a candidate change the odds of the target relation. We introduce BridgeMem, which estimates this quantity as a residual added to the log scores of a frozen full-vocabulary forecaster. For each candidate, BridgeMem retrieves the pair's events that strictly precede t, encodes their relations, directions, and lags, and converts them into a likelihood-ratio correction. A support-adaptive empirical-Bayes reader trusts exact transition counts where they are abundant and backs off to a learned attention estimator where they are sparse. The backbone's own uncertainty gates the correction, so confident queries and candidates without dyadic history are left unchanged. On five benchmarks, BridgeMem improves on the strongest of nine baselines from 2021--2026 in all 20 filtered MRR and Hits@{1,3,10} comparisons, with MRR gains of 0.0213, 0.0164, 0.0216, 0.0112, and 0.0028 over the best prior result. These results show the value of explicit dyadic transition modeling.
Abstract:Temporal knowledge graph forecasting aims to infer future relational facts from the temporal structure of observed events. Existing forecasters mainly summarize history through entity states, relation states, paths, or exact recurrence. These views often miss pair-specific transition evidence, that is, the way prior relations between the query actor and a candidate change the odds of the target relation. We introduce BridgeMem, which estimates this quantity as a residual added to the log scores of a frozen full-vocabulary forecaster. For each candidate, BridgeMem retrieves the pair's events that strictly precede t, encodes their relations, directions, and lags, and converts them into a likelihood-ratio correction. A support-adaptive empirical-Bayes reader trusts exact transition counts where they are abundant and backs off to a learned attention estimator where they are sparse. The backbone's own uncertainty gates the correction, so confident queries and candidates without dyadic history are left unchanged. On five benchmarks, BridgeMem improves on the strongest of nine baselines from 2021--2026 in all 20 filtered MRR and Hits@{1,3,10} comparisons, with MRR gains of 0.0213, 0.0164, 0.0216, 0.0112, and 0.0028 over the best prior result. These results show the value of explicit dyadic transition modeling.
Machine Learning (cs.LG)
arXiv:2609.29268 [cs.LG]
(or arXiv:2609.29268v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.29268 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 285 words
Related coverage
An Explainable Coherence Score for Detecting Temporal Inconsistencies in Political News
arXiv · Sep 1, 2026
RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting
arXiv · Sep 30, 2026
Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding
arXiv · Jun 6, 2026
Graph-centric agentic intelligence
Amazon Science · Oct 1, 2026