Deep Learning

Enhancing Node Representations for Real-World Complex Networks with Topological Augmentation
We present Topological Augmentation (TopoAug), a novel graph augmentation method incorporating higher-order node relations for real-world complex networks, and provide 23 novel real-world graph datasets across various domains.
Xiangyu Zhao, Zehui Li, Mingzhu Shen, Guy-Bart Stan, Pietro Liò, Yiren Zhao
Enhancing Real-World Complex Network Representations with Topological Augmentation
PhD Second Year Project – We present Topological Augmentation (TopoAug), a novel graph augmentation method incorporating higher-order node relations for real-world complex networks, and provide 23 novel real-world graph datasets across various domains.
Xiangyu Zhao, Zehui Li, Mingzhu Shen, Guy-Bart Stan, Pietro Liò, Yiren Zhao
25 Apr 2024
Enhancing Real-World Complex Network Representations with Topological Augmentation
PhD Second Year Project – We present Topological Augmentation (TopoAug), a novel graph augmentation method incorporating higher-order node relations for real-world complex networks, and provide 23 novel real-world graph datasets across various domains.
Xiangyu Zhao, Zehui Li, Mingzhu Shen, Guy-Bart Stan, Pietro Liò, Yiren Zhao
Investigating GNN Expressiveness in Graph Generation Tasks
Imperial UROP 2023 Student Project – We propose an approach to improve GNN-based graph generative models including GCPN, GraphAF and GraphEBM, and investigate the correlation between GNN expressiveness in the graph prediction and graph generation contexts.
Xiandong Zou, Xiangyu Zhao, Pietro Liò, Yiren Zhao
21 Aug 2023
Investigating GNN Expressiveness in Graph Generation Tasks
Imperial UROP 2023 Student Project – We propose an approach to improve GNN-based graph generative models including GCPN, GraphAF and GraphEBM, and investigate the correlation between GNN expressiveness in the graph prediction and graph generation contexts.
Xiandong Zou, Xiangyu Zhao, Pietro Liò, Yiren Zhao
Will More Expressive Graph Neural Networks do Better on Generative Tasks?
We propose an approach to improve GNN-based graph generative models including GCPN, GraphAF and GraphEBM, and investigate the correlation between GNN expressiveness in the graph prediction and graph generation contexts.
Xiandong Zou, Xiangyu Zhao, Pietro Liò, Yiren Zhao
Hybrid Graph: A Unified Graph Representation with Datasets and Benchmarks for Complex Graphs
We introduce the concept of hybrid graphs, a unified definition for higher-order graphs, and present the Hybrid Graph Benchmark (HGB), a collection of hybrid graph datasets with an extensible evaluation framework.
Zehui Li, Xiangyu Zhao, Mingzhu Shen, Guy-Bart Stan, Pietro Liò, Yiren Zhao
Unifying Higher-Order Graph Representation with New Datasets and Benchmarks
PhD First Year Project – We introduce the concept of hybrid graphs, a unified definition for higher-order graphs, and present the Hybrid Graph Benchmark (HGB), a collection of hybrid graph datasets with an extensible evaluation framework.
Zehui Li, Xiangyu Zhao, Mingzhu Shen, Guy-Bart Stan, Pietro Liò, Yiren Zhao
8 Jun 2023
Unifying Higher-Order Graph Representation with New Datasets and Benchmarks
PhD First Year Project – We introduce the concept of hybrid graphs, a unified definition for higher-order graphs, and present the Hybrid Graph Benchmark (HGB), a collection of hybrid graph datasets with an extensible evaluation framework.
Zehui Li, Xiangyu Zhao, Mingzhu Shen, Guy-Bart Stan, Pietro Liò, Yiren Zhao
Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration
We propose GraphAC (Graph Adversarial Collaboration), a conceptually novel, principled, task-agnostic, and stable framework for evaluating GNNs through contrastive self-supervision, without the need of handcrafted augmentations.
Xiangyu Zhao, Hannes Stärk, Dominique Beaini, Yiren Zhao, Pietro Liò