Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning

Li, Zixuan; Jin, Xiaolong; Li, Wei; Guan, Saiping; Guo, Jiafeng; Shen, Huawei; Wang, Yuanzhuo; Cheng, Xueqi

doi:10.1145/3404835.3462963

“…Experimental Setup. We adopt three widelyused datasets, ICEWS14 (Li et al, 2021b), ICEWS18 (Jin et al, 2020), and WIKI (Leblay and Chekol, 2018) to evaluate CEN. Dataset statistics are demonstrated in Table 1.…”

Section: Methodsmentioning

confidence: 99%

“…where RGCN (•) and SC denote the shared RGCN layer and the skip connection unit proposed in RE-GCN (Li et al, 2021b). For the initial timestamp t q − 1, H 2 tq−2 is set to H. R is shared across timestamps, which is different from RE-GCN.…”

Section: Basic Cen Modelmentioning

confidence: 99%

Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning

Li¹,

Guan²,

Jin³

et al. 2022

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Self Cite

View full text Add to dashboard Cite

A Temporal Knowledge Graph (TKG) is a sequence of KGs corresponding to different timestamps. TKG reasoning aims to predict potential facts in the future given the historical KG sequences. One key of this task is to mine and understand evolutional patterns of facts from these sequences. The evolutional patterns are complex in two aspects, lengthdiversity and time-variability. Existing models for TKG reasoning focus on modeling fact sequences of a fixed length, which cannot discover complex evolutional patterns that vary in length. Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on. Thus, we propose a new model, called Complex Evolutional Network (CEN), which uses a length-aware Convolutional Neural Network (CNN) to handle evolutional patterns of different lengths via an easy-to-difficult curriculum learning strategy. Besides, we propose to learn the model under the online setting so that it can adapt to the changes of evolutional patterns over time. Extensive experiments demonstrate that CEN obtains substantial performance improvement under both the traditional offline and the proposed online settings.

show abstract

“…Experimental Setup. We adopt three widelyused datasets, ICEWS14 (Li et al, 2021b), ICEWS18 (Jin et al, 2020), and WIKI (Leblay and Chekol, 2018) CyGNet (Zhu et al, 2021), RE-NET (Jin et al, 2020), xERTE (Han et al, 2020a), TG-Tucker , TG-DistMult , TiTer (Sun et al, 2021) and RE-GCN (Li et al, 2021b). In the experiments, we adopt MRR (Mean Reciprocal Rank) and Hits@{1,3,10} as the metrics for TKG reasoning.…”

Section: Methodsmentioning

confidence: 99%

“…Unlike the query-specific models, entire graph based models encode the latest historical KG sequence of a fixed-length. RE-GCN (Li et al, 2021b) captures the evolutional patterns into the representations of all the entities by modeling KG sequence of a fixed-length at lastest a few timestamps. Glean (Deng et al, 2020) introduces event descriptions to enrich the information of the entities.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning

Li¹,

Guan²,

Jin³

et al. 2022

Preprint

Self Cite

6

0

View full text Add to dashboard Cite

A Temporal Knowledge Graph (TKG) is a sequence of KGs corresponding to different timestamps. TKG reasoning aims to predict potential facts in the future given the historical KG sequences. One key of this task is to mine and understand evolutional patterns of facts from these sequences. The evolutional patterns are complex in two aspects, lengthdiversity and time-variability. Existing models for TKG reasoning focus on modeling fact sequences of a fixed length, which cannot discover complex evolutional patterns that vary in length. Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on. Thus, we propose a new model, called Complex Evolutional Network (CEN), which uses a length-aware Convolutional Neural Network (CNN) to handle evolutional patterns of different lengths via an easy-to-difficult curriculum learning strategy. Besides, we propose to learn the model under the online setting so that it can adapt to the changes of evolutional patterns over time. Extensive experiments demonstrate that CEN obtains substantial performance improvement under both the traditional offline and the proposed online settings.

show abstract