Graph Embedding Methods for Scalable Knowledge Graph Completion
Event details
| Date | 05.09.2022 |
| Hour | 09:00 › 11:00 |
| Speaker | Andrej Janchevski |
| Location | |
| Category | Conferences - Seminars |
EDIC candidacy exam
Exam president: Prof. Pierre Vandergheynst
Thesis advisor: Prof. Volkan Cevher
Co-examiner: Prof. Matthias Grossglauser
Abstract
Knowledge graphs have recently attracted significant attention from both industry and academia in scenarios that require exploiting large-scale heterogeneous data collections. They have witnessed numerous applications in a diverse range: from social media to the telecom industry. Thus, many companies in various industry sectors have started building and maintaining their own knowledge graph for internal use in the last few years. All of the applications of the graph involve reasoning over the heterogeneous relational data it stores, to infer novel information not already present. We refer to this process as knowledge graph completion.
However, modern knowledge graph data possesses an additional property that gives rise to a new challenge: the graphs can contain more than hundreds of millions of entities. When graph sizes reach high orders of magnitude a delicate balance between scalability with respect to model performance on one hand and scalability with respect to computational cost on the other might be required and such a model has yet to be proposed.
In this discussion, we will present three published techniques for scaling up knowledge graph completion, based on graph coarsening, end-to-end learnable graph clustering and improved knowledge graph training query sampling, as well as discuss their benefits and limitations. The gaps in scientific knowledge these and other works on the topic leave motivate our proposed research directions.
Background papers
Exam president: Prof. Pierre Vandergheynst
Thesis advisor: Prof. Volkan Cevher
Co-examiner: Prof. Matthias Grossglauser
Abstract
Knowledge graphs have recently attracted significant attention from both industry and academia in scenarios that require exploiting large-scale heterogeneous data collections. They have witnessed numerous applications in a diverse range: from social media to the telecom industry. Thus, many companies in various industry sectors have started building and maintaining their own knowledge graph for internal use in the last few years. All of the applications of the graph involve reasoning over the heterogeneous relational data it stores, to infer novel information not already present. We refer to this process as knowledge graph completion.
However, modern knowledge graph data possesses an additional property that gives rise to a new challenge: the graphs can contain more than hundreds of millions of entities. When graph sizes reach high orders of magnitude a delicate balance between scalability with respect to model performance on one hand and scalability with respect to computational cost on the other might be required and such a model has yet to be proposed.
In this discussion, we will present three published techniques for scaling up knowledge graph completion, based on graph coarsening, end-to-end learnable graph clustering and improved knowledge graph training query sampling, as well as discuss their benefits and limitations. The gaps in scientific knowledge these and other works on the topic leave motivate our proposed research directions.
Background papers
- Chen, Haochen, Bryan Perozzi, Yifan Hu, and Steven Skiena. “HARP: Hierarchical Representation Learning for Networks.” Proceedings of the AAAI Conference on Artificial Intelligence 32, no. 1 (April 26, 2018). https://doi.org/10.1609/aaai.v32i1.11849.
- Ying, Zhitao, Jiaxuan You, Christopher Morris, Xiang Ren, Will Hamilton, and Jure Leskovec. “Hierarchical Graph Representation Learning with Differentiable Pooling.” In Advances in Neural Information Processing Systems, Vol. 31. Curran Associates, Inc., 2018. https://proceedings.neurips.cc/paper/2018/hash/e77dbaf6759253c7c6d0efc5690369c7-Abstract.html.
- Ren, Hongyu, Hanjun Dai, Bo Dai, Xinyun Chen, Denny Zhou, Jure Leskovec, and Dale Schuurmans. “SMORE: Knowledge Graph Completion and Multi-Hop Reasoning in Massive Knowledge Graphs.” arXiv, November 1, 2021. https://doi.org/10.48550/arXiv.2110.14890.
Practical information
- General public
- Free