Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 2497-2508· 0 citations· 22 references
Abstract
Given a partially observed Temporal Knowledge Graph (TKG), how can we accurately predict missing entities? Unlike static knowledge graphs, TKGs encode facts within temporal contexts, requiring models to reason over both graph structure and time. However, existing TKGC approaches often sample neighbors solely based on temporal proximity, introducing irrelevant context and noise. Moreover, many methods compress snapshots into latent representations and rely on global sequence encoders for temporal modeling, losing edge-level structure and localized relation-specific patterns. In this paper, we propose TiRano (Tensorized Relation-aware temporal reasoning for knowledge graph completion), an accurate and efficient tensor-based temporal reasoning framework for TKGC. TiRano samples relation-adaptive temporal neighbors to construct compact, query-centric subgraphs, thereby reducing noise and computational overhead. Furthermore, TiRano organizes these subgraphs into structure-preserving, time-aligned snapshot tensors, and applies a relation-conditioned temporal convolution, which effectively captures localized edge-level temporal dynamics. Through extensive experiments, we demonstrate that TiRano consistently outperforms state-of-the-art TKGC methods in terms of both prediction accuracy and efficiency, achieving up to 12.3% higher accuracy and 2.4× faster inference.
A Multi-Granularity Implicit Temporal (MGIT) framework that enhances temporal representation and reasoning by modeling implicit temporal dependencies across different granularities is proposed, highlighting its effectiveness in capturing implicit temporal information and enhancing multi-granularity temporal reasoning.
FITTER consistently outperforms inductive baselines without retraining, indicating that vocabulary-agnostic structural learning is a viable foundation for inference over the heterogeneous knowledge graphs of the Semantic Web.
Jia-Xin Pan, M. Nayyeri, Osama Mohammed et al.· 0 citations
: Knowledge graphs organize real-world facts as structured triples and have become a fundamental resource for search engines, question answering, recommender systems, and knowledge-enhanced large language models. However, real-world knowledge graphs remain highly incomplete, which limits their downstream reasoning ability. Existing pre-trained language model-based knowledge graph completion methods provide strong textual semantic representations, but they usually model graph structure only as shallow auxiliary features and remain weak in distinguishing structurally similar entities and topology-near negative samples. To address this limitation, this paper proposes a Dual-Level Structural Context Collaborative Framework (DSC 2 F) for knowledge graph completion. At the instance level, the framework introduces Structural Neighborhood Context (SNC) to inject local neighborhood evidence into the language model input and Relation-Aware Attention (RAA) to condition structural aggregation on the current relation. At the batch level, it constructs topology-aware training batches with biased random walk with restart, so that in-batch negatives are locally related to positive samples and impose stronger structural discrimination pressure. Experiments on WN18RR, FB15k-237, and Wikidata5M show that DSC 2 F achieves the best mean reciprocal rank and Hits@1 on all three datasets, consistently outperforming strong embedding-based and pre-trained language model-based baselines. Ablation studies and structural configuration analyses further verify that SNC, RAA, and Batch-Level Structural Context provide complementary benefits. These results demonstrate that collaborative modeling of instance-level and batch-level structural context can effectively enhance structure-aware entity representation and improve fine-grained entity prediction.
This paper introduces LaGR, a novel approach for integrating global information in knowledge graph reasoning that compresses the graph into a fixed, compact set of latent summaries and applies exact self-attention within this latent space, resulting in scale-invariant attention and stable performance across diverse data settings.
Chen Lin, Lei Wang, Yin Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
