State of the Field
Recent advancements in knowledge graphs are focusing on enhancing their applicability across various domains, particularly through improved link prediction and reasoning capabilities. Techniques like THOR are pushing the boundaries of hyper-relational knowledge graphs by enabling inductive link prediction, which allows models to generalize beyond specific vocabularies. Meanwhile, TKG-Thinker is addressing the challenges of temporal knowledge graph question answering by employing agentic reinforcement learning to facilitate dynamic reasoning, thus overcoming limitations of static prompting strategies. Additionally, frameworks like SynergyKGC are tackling the complexities of heterogeneous graph structures, ensuring robust relational reasoning by reconciling topological mismatches. The integration of domain-specific knowledge graphs with general knowledge graphs is also gaining traction, as seen in recent work on knowledge graph fusion, which aims to enhance coverage and relevance. Collectively, these efforts are paving the way for more efficient and effective applications in areas such as information retrieval, recommendation systems, and automated reasoning.
Papers
1–7 of 7THOR: Inductive Link Prediction over Hyper-Relational Knowledge Graphs
Knowledge graphs (KGs) have become a key ingredient supporting a variety of applications. Beyond the traditional triplet representation of facts where a relation connects two entities, modern KGs obse...
TKG-Thinker: Towards Dynamic Reasoning over Temporal Knowledge Graphs via Agentic Reinforcement Learning
Temporal knowledge graph question answering (TKGQA) aims to answer time-sensitive questions by leveraging temporal knowledge bases. While Large Language Models (LLMs) demonstrate significant potential...
SynergyKGC: Reconciling Topological Heterogeneity in Knowledge Graph Completion via Topology-Aware Synergy
Knowledge Graph Completion (KGC) fundamentally hinges on the coherent fusion of pre-trained entity semantics with heterogeneous topological structures to facilitate robust relational reasoning. Howeve...
Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge
Domain-specific knowledge graphs (DKGs) often lack coverage compared to general knowledge graphs (GKGs). To address this, we introduce Domain-specific Knowledge Graph Fusion (DKGF), a novel task that ...
Return of the Schema: Building Complete Datasets for Machine Learning and Reasoning on Knowledge Graphs
Datasets for the experimental evaluation of knowledge graph refinement algorithms typically contain only ground facts, retaining very limited schema level knowledge even when such information is avail...
Tokenization, Fusion and Decoupling: Bridging the Granularity Mismatch Between Large Language Models and Knowledge Graphs
Leveraging Large Language Models (LLMs) for Knowledge Graph Completion (KGC) is promising but hindered by a fundamental granularity mismatch. LLMs operate on fragmented token sequences, whereas entiti...
Publishing FAIR and Machine-actionable Reviews in Materials Science: The Case for Symbolic Knowledge in Neuro-symbolic Artificial Intelligence
Scientific reviews are central to knowledge integration in materials science, yet their key insights remain locked in narrative text and static PDF tables, limiting reuse by humans and machines alike....