Skip to content

BridgeMem: Causal Dyadic Transition Residuals for Temporal Knowledge Graph Forecasting

Sep 2026 · arXiv.org · Vol abs/2609.29268 · 0 citations · 21 references
Computer Science

TL;DR

BridgeMem is introduced, which estimates the value of explicit dyadic transition modeling as a residual added to the log scores of a frozen full-vocabulary forecaster, and shows the value of explicit dyadic transition modeling in temporal knowledge graph forecasting.

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.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

Time-Aligned Evolving Concept Graphs for Scientific Relation Forecasting

Forecasting scientific relations can guide discovery by identifying promising connections before they emerge. Existing approaches often model concept semantics and graph structure separately or summarize semantics over coarse historical snapshots, leaving semantic representations potentially misaligned with rapidly evo...

Fred Sun, Jing-Ze Wang, Min-Kun Xu et al. · 0 citations
Aug 2026

Adapting Knowledge Graphs for Behavior Denoising in Sequential Recommendation

AdaptedKG is presented, which derives calibrated KG evidence for each training example without adding graph representations to the recommendation model and compares the observed context with structurally matched alternatives to identify relational paths that are unusually prominent and uses them to build a local KG vie...

Zichun Jin, Zihan Zhou, Yi-Nan Liu et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Coupling Noisy Pairwise Knowledge to the DAG Posterior for Causal Discovery

External causal reports can improve structure learning from limited observations, but their reliability varies across sources and variable pairs. We introduce HB-NoisyKG, a Bayesian framework that combines observational data with repeated causal reports from sources such as large language models. Each report is a noisy...

Guoliang Xu, James E. Corter · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.