Adaptive Convolution for Multi-Relational Learning

By Xiaotian Jiang, Quan Wang, Bin Wang. 2019

167 citations recorded by the source corpus.

We consider the problem of learning distributed representations for entities and relations of multi-relational data so as to predict missing links therein. Convolutional neural networks have recently shown their superiority for this problem, bringing increased model expressiveness while remaining parameter efficient. Despite the success, previous convolution designs fail to model full interactions between input entities and relations, which potentially limits the performance of link prediction. In this work we introduce ConvR, an adaptive convolutional network designed to maximize entity-relation interactions in a convolutional fashion. ConvR adaptively constructs convolution filters from relation representations, and applies these filters across entity representations to generate convolutional features. As such, ConvR enables rich interactions between entity and relation representations at diverse regions, and all the convolutional features generated will be able to capture such interactions. We evaluate ConvR on multiple benchmark datasets. Experimental results show that: (1) ConvR performs substantially better than competitive baselines in almost all the metrics and on all the datasets; (2) Compared with state-of-the-art convolutional models, ConvR is not only more effective but also more efficient. It offers a 7% increase in MRR and a 6% increase in Hits@10, while saving 12% in parameter storage.

Subfields: Artificial Intelligence, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Shiji Song
2. Yulin Wang
3. Gao Huang
4. Partha P. Talukdar
5. Le Yang
6. Yizeng Han
7. Honghui Wang
8. Xirui Ke

In Graph Learning

1. Xinwang Liu
2. Partha P. Talukdar
3. Soumya Sanyal
4. Shikhar Vashishth
5. Vikram Nitin

Citations in the corpus

• Dynamic Neural Networks: A Survey (2021, background): “Others Time series forecasting [248], [249], [250], Link prediction [251], Recommendation system [77], [252], [253], [254] Graph classification [121], Document classification [156], [255], [256], [257], Stereo confidence estimation [258]”
• Composition-based Multi-Relational Graph Convolutional Networks (2019, methodology): “The scores of baseline methods are taken directly from the previous papers (Sun et al., 2019; Cai & Wang, 2018; Shang et al., 2019; Balažević et al., 2019; Jiang et al., 2019; Ye et al., 2019).”
• Knowledge Graph Embedding for Link Prediction (2020, methodology): “The included models are: DistMult [71]; ComplEx [61]; ANALOGY [35]; SimplE [27]; HolE [46]; TuckER [6]; TransE [8]; STransE [41]; CrossE [72]; TorusE [13]; RotatE [55]; ConvE [11]; ConvKB [42]; ConvR [25]; CapsE [43]; RSN [19].”
• Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, methodology): “P Q (Bordes et al., 2013) force h þ r to be close to t TransH (Wang et al., 2014) project entities into the relation-speci fi c hyperplane TransR (Lin et al., 2015) project entities and relations in separate spaces TransD (Ji et al., 2015) determine the project matrices by both entities and relations”
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, methodology): “Besides, ConvR [69] designs an adaptive convolutional network to maximize entity-relation interactions by constructing convolution filters across the entity and relation representations.”