Learning Multi-graph Structure for Temporal Knowledge Graph Reasoning

• URL: http://arxiv.org/abs/2312.03004v2
• Date: Mon, 26 Feb 2024 06:12:49 GMT
• Title: Learning Multi-graph Structure for Temporal Knowledge Graph Reasoning
• Authors: Jinchuan Zhang, Bei Hui, Chong Mu, Ling Tian
• Abstract summary: This paper proposes an innovative reasoning approach that focuses on Learning Multi-graph Structure (LMS) LMS incorporates an adaptive gate for merging entity representations both along and across timestamps effectively. It also integrates timestamp semantics into graph attention calculations and time-aware decoders.
• Score: 3.3571415078869955
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal Knowledge Graph (TKG) reasoning that forecasts future events based on historical snapshots distributed over timestamps is denoted as extrapolation and has gained significant attention. Owing to its extreme versatility and variation in spatial and temporal correlations, TKG reasoning presents a challenging task, demanding efficient capture of concurrent structures and evolutional interactions among facts. While existing methods have made strides in this direction, they still fall short of harnessing the diverse forms of intrinsic expressive semantics of TKGs, which encompass entity correlations across multiple timestamps and periodicity of temporal information. This limitation constrains their ability to thoroughly reflect historical dependencies and future trends. In response to these drawbacks, this paper proposes an innovative reasoning approach that focuses on Learning Multi-graph Structure (LMS). Concretely, it comprises three distinct modules concentrating on multiple aspects of graph structure knowledge within TKGs, including concurrent and evolutional patterns along timestamps, query-specific correlations across timestamps, and semantic dependencies of timestamps, which capture TKG features from various perspectives. Besides, LMS incorporates an adaptive gate for merging entity representations both along and across timestamps effectively. Moreover, it integrates timestamp semantics into graph attention calculations and time-aware decoders, in order to impose temporal constraints on events and narrow down prediction scopes with historical statistics. Extensive experimental results on five event-based benchmark datasets demonstrate that LMS outperforms state-of-the-art extrapolation models, indicating the superiority of modeling a multi-graph perspective for TKG reasoning.

Related papers

• Learning Granularity Representation for Temporal Knowledge Graph Completion [2.689675451882683]
  Temporal Knowledge Graphs (TKGs) incorporate temporal information to reflect the dynamic structural knowledge and evolutionary patterns of real-world facts. This paper proposes textbfLearning textbfGranularity textbfRepresentation (termed $mathsfLGRe$) for TKG completion. It comprises two main components: Granularity Learning (GRL) and Adaptive Granularity Balancing (AGB)
  arXiv  Detail & Related papers  (2024-08-27T08:19:34Z)
• Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning [5.510391547468202]
  Temporal Knowledge Graph (TKG) reasoning focuses on predicting events through historical information within snapshots distributed on a timeline. We propose an innovative TKG reasoning approach towards textbfHistorically textbfRelevant textbfEvents textbfStructuring ($mathsfHisRES$)
  arXiv  Detail & Related papers  (2024-05-17T08:33:43Z)
• PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equations [49.80959046861793]
  We present PDETime, a novel LMTF model inspired by the principles of Neural PDE solvers. Our experimentation across seven diversetemporal real-world LMTF datasets reveals that PDETime adapts effectively to the intrinsic nature of the data.
  arXiv  Detail & Related papers  (2024-02-25T17:39:44Z)
• TimeGraphs: Graph-based Temporal Reasoning [64.18083371645956]
  TimeGraphs is a novel approach that characterizes dynamic interactions as a hierarchical temporal graph. Our approach models the interactions using a compact graph-based representation, enabling adaptive reasoning across diverse time scales. We evaluate TimeGraphs on multiple datasets with complex, dynamic agent interactions, including a football simulator, the Resistance game, and the MOMA human activity dataset.
  arXiv  Detail & Related papers  (2024-01-06T06:26:49Z)
• Learning Time-aware Graph Structures for Spatially Correlated Time Series Forecasting [30.93275270960829]
  We propose Time-aware Graph Structure Learning (TagSL), which extracts time-aware correlations among time series. We also present a Graph Convolution-based Gated Recurrent Unit (GCGRU), that jointly captures spatial and temporal dependencies. Finally, we introduce a unified framework named Time-aware Graph Convolutional Recurrent Network (TGCRN), combining TagSL, GCGRU in an encoder-decoder architecture for multi-step-temporal forecasting.
  arXiv  Detail & Related papers  (2023-12-27T04:23:43Z)
• Generic Temporal Reasoning with Differential Analysis and Explanation [61.96034987217583]
  We introduce a novel task named TODAY that bridges the gap with temporal differential analysis. TODAY evaluates whether systems can correctly understand the effect of incremental changes. We show that TODAY's supervision style and explanation annotations can be used in joint learning.
  arXiv  Detail & Related papers  (2022-12-20T17:40:03Z)
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs [65.18780403244178]
  We propose a continuous model to forecast Multivariate Time series with dynamic Graph neural Ordinary Differential Equations (MTGODE) Specifically, we first abstract multivariate time series into dynamic graphs with time-evolving node features and unknown graph structures. Then, we design and solve a neural ODE to complement missing graph topologies and unify both spatial and temporal message passing.
  arXiv  Detail & Related papers  (2022-02-17T02:17:31Z)
• EvoKG: Jointly Modeling Event Time and Network Structure for Reasoning over Temporal Knowledge Graphs [25.408246523764085]
  Reasoning over temporal knowledge graphs (TKGs) is crucial for many applications to provide intelligent services. We present a problem formulation that unifies the two major problems that need to be addressed for an effective reasoning over TKGs, namely, modeling the event time and the evolving network structure. Our proposed method EvoKG jointly models both tasks in an effective framework, which captures the ever-changing structural and temporal dynamics in TKGs.
  arXiv  Detail & Related papers  (2022-02-15T18:49:53Z)
• Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning [59.004025528223025]
  Key to predict future facts is to thoroughly understand the historical facts. A TKG is actually a sequence of KGs corresponding to different timestamps. We propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN)
  arXiv  Detail & Related papers  (2021-04-21T05:12:21Z)
• TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation [12.138550487430807]
  We present a new approach of TKG embedding, TeRo, which defines the temporal evolution of entity embedding. We show our proposed model overcomes the limitations of the existing KG embedding models and TKG embedding models. Experimental results on four different TKGs show that TeRo significantly outperforms existing state-of-the-art models for link prediction.
  arXiv  Detail & Related papers  (2020-10-02T14:35:27Z)
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks [91.65637773358347]
  We propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module. Our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets.
  arXiv  Detail & Related papers  (2020-05-24T04:02:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.