Temporal Inductive Path Neural Network for Temporal Knowledge Graph Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911764267925504 |
|---|---|
| author | Dong, Hao Wang, Pengyang Xiao, Meng Ning, Zhiyuan Wang, Pengfei Zhou, Yuanchun |
| author_facet | Dong, Hao Wang, Pengyang Xiao, Meng Ning, Zhiyuan Wang, Pengfei Zhou, Yuanchun |
| contents | Temporal Knowledge Graph (TKG) is an extension of traditional Knowledge Graph (KG) that incorporates the dimension of time. Reasoning on TKGs is a crucial task that aims to predict future facts based on historical occurrences. The key challenge lies in uncovering structural dependencies within historical subgraphs and temporal patterns. Most existing approaches model TKGs relying on entity modeling, as nodes in the graph play a crucial role in knowledge representation. However, the real-world scenario often involves an extensive number of entities, with new entities emerging over time. This makes it challenging for entity-dependent methods to cope with extensive volumes of entities, and effectively handling newly emerging entities also becomes a significant challenge. Therefore, we propose Temporal Inductive Path Neural Network (TiPNN), which models historical information in an entity-independent perspective. Specifically, TiPNN adopts a unified graph, namely history temporal graph, to comprehensively capture and encapsulate information from history. Subsequently, we utilize the defined query-aware temporal paths on a history temporal graph to model historical path information related to queries for reasoning. Extensive experiments illustrate that the proposed model not only attains significant performance enhancements but also handles inductive settings, while additionally facilitating the provision of reasoning evidence through history temporal graphs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_03251 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Temporal Inductive Path Neural Network for Temporal Knowledge Graph Reasoning Dong, Hao Wang, Pengyang Xiao, Meng Ning, Zhiyuan Wang, Pengfei Zhou, Yuanchun Artificial Intelligence Machine Learning Temporal Knowledge Graph (TKG) is an extension of traditional Knowledge Graph (KG) that incorporates the dimension of time. Reasoning on TKGs is a crucial task that aims to predict future facts based on historical occurrences. The key challenge lies in uncovering structural dependencies within historical subgraphs and temporal patterns. Most existing approaches model TKGs relying on entity modeling, as nodes in the graph play a crucial role in knowledge representation. However, the real-world scenario often involves an extensive number of entities, with new entities emerging over time. This makes it challenging for entity-dependent methods to cope with extensive volumes of entities, and effectively handling newly emerging entities also becomes a significant challenge. Therefore, we propose Temporal Inductive Path Neural Network (TiPNN), which models historical information in an entity-independent perspective. Specifically, TiPNN adopts a unified graph, namely history temporal graph, to comprehensively capture and encapsulate information from history. Subsequently, we utilize the defined query-aware temporal paths on a history temporal graph to model historical path information related to queries for reasoning. Extensive experiments illustrate that the proposed model not only attains significant performance enhancements but also handles inductive settings, while additionally facilitating the provision of reasoning evidence through history temporal graphs. |
| title | Temporal Inductive Path Neural Network for Temporal Knowledge Graph Reasoning |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2309.03251 |