The paper introduces a time‑aligned evolving concept graph framework that jointly models semantic and structural changes in scientific literature. By treating dated papers as shared update events, it reconstructs both semantic and structural states from the same publication history for each prediction time, and fuses these states at the pair level to forecast co‑occurrence, relation formation, and conditional relation type. Experiments on a large graph of 187,848 papers and 270,687 concepts show that refreshing context with graph updates boosts mean relation AUPRC by 16.6% and raises mean relation AUROC from 0.9290 to 0.9722.
Forecasting scientific relations can guide discovery by identifying promising connections before they emerge. Existing approaches often model concept semantics and graph structure separately or summar...
The paper introduces EvoTree, a staged framework for automatically generating evolution trees from citation graphs. It separates backbone learning from temporal refinement, using a graph-aware encoder and hierarchical clustering to build a stable taxonomy, then fine-tunes temporally to attach marginal papers under monotonic-path constraints, and finally labels concepts with an LLM without changing the topology. The authors release an annotated benchmark across 11 AI subfields and report that EvoTree outperforms baselines in NMI, citation-direction accuracy, concept purity, and marginal-paper detection.
arXiv:2607. 09232v1 Announce Type: new Abstract: Temporal knowledge graphs (TKGs) represent evolving relational systems, whose underlying data-generating processes often change over time.
arXiv:2607. 02872v1 Announce Type: new Abstract: Dynamic knowledge graphs are ubiquitous in today's AI applications, as we represent molecular structures, social relationships, and language information using these graph models.
Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but they scale poorly against the current rate of publication. Existing taxonomy-induction methods are la...
Hakken is a domain‑agnostic system that predicts and explains future scientific discoveries by combining transformer‑based models trained on temporal knowledge graphs with large language model semantic knowledge. It identifies novel relationships between scientific concepts that extend beyond the deductive hull of existing knowledge and provides explanations to help scientists assess these predictions. In the biomedical domain, Hakken set a new benchmark for time‑aware multi‑label relation prediction, generated 1.5 million high‑confidence hypotheses about aging, and experimentally confirmed two predictions that revealed previously undocumented interactions relevant to drug discovery.
arXiv:2608.29612v1 Announce Type: new Abstract: Sustained scientific work requires a knowledge substrate that carries interpretation across tasks and preserves paths to source evidence. We call this...
arXiv:2607. 08490v1 Announce Type: new Abstract: Biomedical language evolves rapidly as new discoveries emerge, causing traditional text models to lose semantic fidelity over time.
arXiv:2608. 10668v1 Announce Type: new 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.
arXiv:2606. 16509v1 Announce Type: new Abstract: Link prediction in knowledge graphs fundamentally depends on the quality of learned embeddings for entities and relations.
arXiv:2606. 09105v1 Announce Type: new Abstract: Generating novel, feasible, and high-quality research ideas is an important yet challenging task in scientific discovery.
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.