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.
Abstract
Temporal knowledge graphs are central to many uses of the Semantic Web, but existing completion methods assume the entities, relation names, and timestamps to be reasoned about are already known at training time, restricting each model to a single graph and vocabulary. We propose FITTER, the first fully-inductive structural model for temporal knowledge graph link prediction that supports cross-domain transfer: the inference graph may contain entirely unseen entities, relation names, and timestamps drawn from a different domain. FITTER represents each predicate by its interaction patterns with others and time through encodings of relative rather than absolute ordering; message-passing fuses local and global temporal context to produce vocabulary-agnostic embeddings. We prove the temporal encoding is time-shift invariant and evaluate FITTER on cross-domain, cross-graph transfer over six temporal knowledge graph benchmarks of diverse domains, granularities, and time spans. 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.
AG is proposed, a Structure-Aware Generative framework for temporal knowledge graph reasoning with historical evidence that first constructs dual-view historical evidence to better capture structural dependencies in temporal knowledge graphs and formulates TKGR as an end-to-end generative task through instruction tuning.
Zihao Jiang, Wenjie Xu, Miao Peng et al.· World wide web (Bussum)· 0 citations
The Temporal-Weighted Transfer Network (TWTNET), a novel reasoning model that jointly leverages statistical modeling and historical information transfer, is proposed, which achieves more robust and interpretable extrapolative reasoning.
Hongyu Hao, Yifan Zhang, Xinru Zhao et al.· ACM Transactions on Intellig...· 0 citations
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.
Knowledge graph foundation models such as Ultra and Trix achieve strong inductive transfer by learning relation-graph representations that generalise to unseen entities and relations. Extending this transferability to temporal knowledge graphs (TKGs) remains challenging: existing temporal models tie their parameters to dataset-specific entities, relations, or timestamps and are not designed to transfer to TKGs with disjoint vocabularies. We propose GRATE (Gated Rotary Attention for Temporal Encoding), an entity-side message function that adds no learnable parameters and encodes time through relative time differences by rotating each edge message according to its time gap to the query and applying a query-conditioned gate to select temporally relevant signals. GRATE integrates into NBFNet-style KG foundation models while preserving structural transferability. Existing TKG benchmarks evaluate within shared train/test vocabularies and cannot directly test cross-dataset temporal transfer; we therefore construct GDELTIndT and WIKIIndT, inductive transfer benchmark suites with disjoint entities, relations, and timestamps spanning both interpolation and extrapolation. Across these benchmarks and held-out forecasting datasets, a single jointly pretrained GRATE checkpoint improves over the static base model in most settings.
Jiaxin Pan, Osama Mohammed, Daniel Hernández et al.· 0 citations
This framework performs LLM knowledge elicitation to extract factual knowledge from the model’s internal representations and transforms sentence-level representations into entity-level representations and aligns them within a unified space.
Deyu Chen, Qiyuan Li, Jinguang Gu et al.· 0 citations
