Disentangled Multi-span Evolutionary Network against Temporal Knowledge Graph Reasoning

Temporal Knowledge Graphs (TKGs) incorporate the temporal feature to express the transience of knowledge by describing when facts occur.TKG extrapolation aims to infer possible future facts based on known history, which has garnered significant attention in recent years.Some existing methods treat TKG as a sequence of independent subgraphs to model temporal evolution patterns, demonstrating impressive reasoning performance.However, they still have limitations: 1) In modeling subgraph semantic evolution, they usually neglect the internal structural interactions between subgraphs, which are actually crucial for encoding TKGs.2) They overlook the potential smooth features that do not lead to semantic changes, which should be distinguished from the semantic evolution process.Therefore, we propose Disentangled Multi-span Evolutionary Network (DiMNet) for TKG reasoning.Specifically, we design a multi-span evolution strategy that captures local neighbor features while perceiving historical neighbor semantic information, thus enabling internal interactions between subgraphs during the evolution process.To maximize the capture of semantic change patterns, we design a disentangle component that adaptively separates nodes' active and stable features, used to dynamically control the influence of historical semantics on future evolution.Extensive experiments demonstrate that DiMNet achieves substantial performance in TKG reasoning, outperforming the state-of-theart up to 22.7% in MRR. Related WorkWe briefly review the classic traditional KG reasoning methods and then introduce some recent related TKG reasoning methods.