Machine Learning based Graph Enhancement by Complementation, Fusion, and Transferring
Machine Learning based Graph Enhancement by Complementation, Fusion, and Transferring
- 주제(키워드) Machine Learning , Semi-Supervised Learning , Bioinformatics
- 발행기관 아주대학교
- 지도교수 신현정
- 발행년도 2019
- 학위수여년월 2019. 8
- 학위명 박사
- 학과 및 전공 일반대학원 산업공학과
- 실제URI http://www.dcollection.net/handler/ajou/000000029319
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
When data is expressed in a graph which consists of nodes and edges, there is an advantage that a relationship of data can be visually expressed. With a graph, machine learning can perform the prediction tasks. However, most of the real world data is sparse, and the number of labeled data is very small. In this case, machine learning cannot provide sufficient inference. In order to make prediction performance better in machine learning using graph, the graph should contain a lot of information (dense graph), or a lot of label information. To motivate this, we propose a graph enhancement learning. It consists of three algorithm; (1) edge complementation, (2) partial graph fusion, and (3) label transferring. Edge complementation is incremental learning to enhance disconnected edges in a sparse graph. Partial graph fusion is one of graph integration method. Combinations of many partial graphs help prediction tasks. To circumvent deficiency of lack of labeled data, we propose label transferring algorithms which generate pseudo-labels. The graph enhancement learning was applied to the biomedical graph. The edges of the disease network were complemented to find co-occurrence disease. In addition, the edge of the drug network was complemented to find the candidate drug. Gene networks combined with partial gene networks to identify key target genes for immune disease. To circumvent deficiency of lack of labeled data, we propose label transferring algorithms which generate pseudo-labels. And it is applied five benchmark dataset. When edges are not enough or labeled data is insufficient, the prediction performance of machine learning can be improved through graph enhancement learning.
more목차
1. Introduction
2. Fundamentals: Biomedical Graph
2.1. Disease Network
2.2. Drug Target-Protein Network
2.3. Gene Network
3.Fundamentals: Graph-based Semi-Supervised Learning
3.1. Semi-Supervised Classification
3.2. Semi-Supervised Scoring
4. Edge Complementation
4.1. Complementation algorithm
4.2. Experiment I: Disease Network
4.3. Experiment II: Drug Network
5. Partial Graph Fusion
5.1. Graph Fusion with useful partial graphs
5.2. Semi-Supervised Scoring with integrated graph
5.3. Experiment: Gene Network
6. Label Transferring
6.1. Pseudo-label propagation with graph abstraction
6.2. Experiment: Benchmark dataset
7. Conclusion
References
