Graph-structured data (GSD) is ubiquitous in real-life applications, which appears in many learning applications such as property prediction for molecular graphs, product recommendations from heterogeneous information networks, and logical queries from knowledge graphs. Recently, learning from graph-structured data has also become a research focus in the machine learning community. However, again due to such diversities in GSD, there are no universal learning models that can perform well and consistently across different learning applications based on graphs. In sharp contrast to this, convolutional neural networks work well on natural images, and transformers are good choices for text data. In this tutorial, we will talk about using automated machine learning (AutoML) as a tool to design learning models for GSD. Specifically, we will elaborate on what is AutoML, what kind of prior information from graphs can be explored by AutoML, and how can insights be generated from the searched models.
|7:30-8:15||Part 1: Automated Graph Neural Network [Slides]|
|Speaker: Huan Zhao|
|8:15-9:00||Part 2: Hyper-parameter Tuning for Graph-Structured Data. [Slides]|
|Speaker: Quanming Yao|
|9:00-9:45||Part 3: Automated Knowledge Graph Reasoning: from Triplets to Subgraphs [Slides]|
|Speaker: Yongqi Zhang|
|9:45-10:00||Part 4: Discussion|
Quanming Yao, EE Department, Tsinghua University. Beijing. China.
Huan Zhao, 4Paradigm Inc. Beijing. China.
Yongqi Zhang, 4Paradigm Inc. Beijing. China.
- ACML 2021 Tutorial: Automated Learning form Graph-Structured Data
- IJCAI 2021 Tutorial: Automated Recommender System Tutorial
- KDD 2020 Tutorial: Advances in Recommender Systems
Due to the space limitation, we only list highly-related papers.
- Y. Zhang, Q. Yao. Knowledge Graph Reasoning with Relational Digraph. WebConf. 2022.
- L. Wei, H. Zhao, Z. He. Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective. WebConf. 2022.
- K. Zhou, Z. Liu, K. Duan. X. Hu. Graph Neural Networks: AutoML in book "Graph Neural Networks: Foundations, Frontiers, and Applications". 2022
- X. Wang, Z. Zhang, W. Zhu. Automated Graph Machine Learning: Approaches, Libraries and Directions. arXiv preprint, 2022.
- Y. Zhang, Q. Yao, L. Chen. Efficient, Simple and Automated Negative Sampling for Knowledge Graph Embedding. VLDBJ. 2021.
- X. Wang, S. Fan, K. Kuang, W. Zhu. Explainable Automated Graph Representation Learning with Hyperparameter Importance. ICML 2021.
- Y. Ding, Q. Yao, H. Zhao, T. Zhang. DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks. KDD. 2021.
- H. Zhao, Q. Yao, and W. Tu, Search to aggregate neighborhood for graph neural network, in ICDE, 2021.
- L. Wei, H. Zhao, Q. Yao, Z. He. Pooling Architecture Search for Graph Classification. CIKM. 2021.
- J. You, R. Ying, and J. Leskovec, Design Space for Graph Neural Networks, in NeurIPS, 2020.
- Y. Zhang, Q. Yao, W. Dai and L. Chen, AutoSF: Searching Scoring Functions for Knowledge Graph Embedding, in ICDE 2020.
- Y. Zhang, Q. Yao and L. Chen, Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding, in NeurIPS 2020.
- F. Hutter, L. Kotthoff, and J. Vanschoren, Automated machine learning: methods, systems, challenges, Springer Nature, 2019.
- Q. Yao and M. Wang, Taking human out of learning applications: A survey on automated machine learning, tech. rep., arXiv preprint, 2018.