Cycle Representation Learning for Inductive Relation Prediction

Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Chao Chen
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:24895-24910, 2022.

Abstract

In recent years, algebraic topology and its modern development, the theory of persistent homology, has shown great potential in graph representation learning. In this paper, based on the mathematics of algebraic topology, we propose a novel solution for inductive relation prediction, an important learning task for knowledge graph completion. To predict the relation between two entities, one can use the existence of rules, namely a sequence of relations. Previous works view rules as paths and primarily focus on the searching of paths between entities. The space of rules is huge, and one has to sacrifice either efficiency or accuracy. In this paper, we consider rules as cycles and show that the space of cycles has a unique structure based on the mathematics of algebraic topology. By exploring the linear structure of the cycle space, we can improve the searching efficiency of rules. We propose to collect cycle bases that span the space of cycles. We build a novel GNN framework on the collected cycles to learn the representations of cycles, and to predict the existence/non-existence of a relation. Our method achieves state-of-the-art performance on benchmarks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-yan22a, title = {Cycle Representation Learning for Inductive Relation Prediction}, author = {Yan, Zuoyu and Ma, Tengfei and Gao, Liangcai and Tang, Zhi and Chen, Chao}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {24895--24910}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/yan22a/yan22a.pdf}, url = {https://proceedings.mlr.press/v162/yan22a.html}, abstract = {In recent years, algebraic topology and its modern development, the theory of persistent homology, has shown great potential in graph representation learning. In this paper, based on the mathematics of algebraic topology, we propose a novel solution for inductive relation prediction, an important learning task for knowledge graph completion. To predict the relation between two entities, one can use the existence of rules, namely a sequence of relations. Previous works view rules as paths and primarily focus on the searching of paths between entities. The space of rules is huge, and one has to sacrifice either efficiency or accuracy. In this paper, we consider rules as cycles and show that the space of cycles has a unique structure based on the mathematics of algebraic topology. By exploring the linear structure of the cycle space, we can improve the searching efficiency of rules. We propose to collect cycle bases that span the space of cycles. We build a novel GNN framework on the collected cycles to learn the representations of cycles, and to predict the existence/non-existence of a relation. Our method achieves state-of-the-art performance on benchmarks.} }
Endnote
%0 Conference Paper %T Cycle Representation Learning for Inductive Relation Prediction %A Zuoyu Yan %A Tengfei Ma %A Liangcai Gao %A Zhi Tang %A Chao Chen %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-yan22a %I PMLR %P 24895--24910 %U https://proceedings.mlr.press/v162/yan22a.html %V 162 %X In recent years, algebraic topology and its modern development, the theory of persistent homology, has shown great potential in graph representation learning. In this paper, based on the mathematics of algebraic topology, we propose a novel solution for inductive relation prediction, an important learning task for knowledge graph completion. To predict the relation between two entities, one can use the existence of rules, namely a sequence of relations. Previous works view rules as paths and primarily focus on the searching of paths between entities. The space of rules is huge, and one has to sacrifice either efficiency or accuracy. In this paper, we consider rules as cycles and show that the space of cycles has a unique structure based on the mathematics of algebraic topology. By exploring the linear structure of the cycle space, we can improve the searching efficiency of rules. We propose to collect cycle bases that span the space of cycles. We build a novel GNN framework on the collected cycles to learn the representations of cycles, and to predict the existence/non-existence of a relation. Our method achieves state-of-the-art performance on benchmarks.
APA
Yan, Z., Ma, T., Gao, L., Tang, Z. & Chen, C.. (2022). Cycle Representation Learning for Inductive Relation Prediction. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:24895-24910 Available from https://proceedings.mlr.press/v162/yan22a.html.

Related Material