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.
By Fred Sun, Jingze Wang, Minkun Xu, Shangqi Guo
arXiv:2607. 09232v1 Announce Type: new Abstract: Temporal knowledge graphs (TKGs) represent evolving relational systems, whose underlying data-generating processes often change over time.
By Konrad \"Ozdemir, Julia Gastinger, Lukas Kirchdorfer, Heiner Stuckenschmidt
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.
By Zexing Zhao, Yuntong Hu, Liang Zhao
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.
By Nan Fang, Yijun Wang, Hao Liao, Sikun Yang
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.
By Tarek R. Besold, Uchenna Akujuobi, Pablo Sanchez, Alessandra Toniato, Kana Maruyama, Jihun Choi, Samy Badreddine, Frederick Gifford, Daniel Evans-Yamamoto, Sucheendra K. Palaniappan, Miquel Ferrer, Kae Nagano, Iris Rossell, Tom Joy, Hatem ElShazly, Chrysa Iliopoulou, Christoph Wehner, Thiviyan Thanapalasingam, Susana Nunes, Pedro G. Cotovio, Peter Wurman, Peter Stone, Hiroaki Kitano, Michael Spranger
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...
By Shi-Ju Ran, Kun Zhang, Xi Wu, Liu-Si Yang, Wen-Jun Li
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.
By Bharathwaj Vijayakumar, Sahana K. Varadaraju
C-Unseen is a self‑interpretable framework designed to detect weak signals in Dynamic Temporal Knowledge Graphs (DTKGs). It defines a weak signal as a rare, semantically coherent subgraph that spreads across consecutive snapshots. The system uses a Rare Subgraphs Extractor, where a large language model identifies subgraphs that contrast with the dominant narrative through chain‑of‑thought reasoning, and a Weak Signal Alerter that tracks the persistence of these subgraphs over time to isolate true weak signals, outperforming keyword, topic, and graph‑based baselines.
By Yassir Lairgi, Ludovic Moncla, Khalid Benabdeslem, R\'emy Cazabet, Pierre Cl\'eau
arXiv:2606. 16509v1 Announce Type: new Abstract: Link prediction in knowledge graphs fundamentally depends on the quality of learned embeddings for entities and relations.
By Mohommad Esmaei Khani, Mahdieh Hasheminejad, Ali Taherkhani, Hossein Hajiabolhassan
arXiv:2605. 07121v2 Announce Type: replace Abstract: Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events.
By Seunghan Lee, Jun Seo, Jaehoon Lee, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, SoonYoung Lee, Wonbin Ahn
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.
By Jiaxin Pan, Mojtaba Nayyeri, Osama Mohammed, Daniel Hernandez, Rongchuan Zhang, Cheng Cheng, Steffen Staab