VITA: Versatile Time Representation Learning for Temporal Hyper-Relational Knowledge Graphs
Knowledge graphs (KGs) have become an effective paradigm for managing real-world facts, which are not only complex but also dynamically evolve over time. The temporal validity of facts often serves as a strong clue in downstream link prediction tasks, which predicts a missing element in a fact. Traditional link prediction techniques on temporal KGs either consider a sequence of temporal snapshots of KGs with an ad-hoc defined time interval or expand a temporal fact over its validity period under a predefined time granularity; these approaches not only suffer from the sensitivity of the selection of time interval/granularity, but also face the computational challenges when handling facts with long (even infinite) validity. Although the recent hyper-relational KGs represent the temporal validity of a fact as qualifiers describing the fact, it is still suboptimal due to its ignorance of the infinite validity of some facts and the insufficient information encoded from the qualifiers about the temporal validity. Against this background, we propose VITA, a $\underline{V}$ersatile t$\underline{I}$me represen$\underline{TA}$tion learning method for temporal hyper-relational knowledge graphs. We first propose a versatile time representation that can flexibly accommodate all four types of temporal validity of facts (i.e., since, until, period, time-invariant), and then design VITA to effectively learn the time information in both aspects of time value and timespan to boost the link prediction performance. We conduct a thorough evaluation of VITA compared to a sizable collection of baselines on real-world KG datasets. Results show that VITA outperforms the best-performing baselines in various link prediction tasks (predicting missing entities, relations, time, and other numeric literals) by up to 75.3%. Ablation studies and a case study also support our key design choices.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge GraphsLink PredictionRepresentation LearningSimilar Papers 제목 키워드 기반
$\text{H}^2\text{TNE}$: Temporal Heterogeneous Information Network Embedding in Hyperbolic Spaces
Temporal heterogeneous information network (temporal HIN) embedding, aiming to represent various types of nodes of different timestamps into low dimensional spaces while preserving structural and semantic information, is…
Link PredictionNetwork EmbeddingNode ClassificationRepresentation Learning+1Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction
Crime has become a major concern in many cities, which calls for the rising demand for timely predicting citywide crime occurrence. Accurate crime prediction results are vital for the beforehand decision-making of govern…
Crime PredictionDecision MakingSelf-Supervised LearningVitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications
As LLM-based agents are increasingly deployed in real-life scenarios, existing benchmarks fail to capture their inherent complexity of handling extensive information, leveraging diverse resources, and managing dynamic us…
Hypergraph-Based Dynamic Graph Node Classification
Node classification on static graphs has achieved significant success, but achieving accurate node classification on dynamic graphs where node topology, attributes, and labels change over time has not been well addressed…
ClassificationNode ClassificationDiscrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space
Representation learning over temporal networks has drawn considerable attention in recent years. Efforts are mainly focused on modeling structural dependencies and temporal evolving regularities in Euclidean space which,…
Graph EmbeddingGraph Neural NetworkLink PredictionNetwork Embedding+1