422 citations · 1.5k across the 47 of their papers we have counts for
26 papers · 1 filter
A Markov Random Field model for Hypergraph-based Machine Learning
Bohan Tang, Keyue Jiang, Laura Toni +2
Understanding the data-generating process is essential for building machine learning models that generalise well while ensuring robustness and interpretability. This paper addresse…
Structure-Aware Robustness Certificates for Graph Classification
Pierre Osselin, Henry Kenlay, Xiaowen Dong
Certifying the robustness of a graph-based machine learning model poses a critical challenge for safety. Current robustness certificates for graph classifiers guarantee output inva…
Graph Classification Gaussian Processes via Spectral Features
Felix L. Opolka, Yin-Cong Zhi, Pietro Liò +1
Graph classification aims to categorise graphs based on their structure and node attributes. In this work, we propose to tackle this task using tools from graph signal processing b…
Bayesian Optimisation of Functions on Graphs
Xingchen Wan, Pierre Osselin, Henry Kenlay +3
The increasing availability of graph-structured data motivates the task of optimising over functions defined on the node set of graphs. Traditional graph search algorithms can be a…
DRew: Dynamically Rewired Message Passing with Delay
Benjamin Gutteridge, Xiaowen Dong, Michael Bronstein +1
Message passing neural networks (MPNNs) have been shown to suffer from the phenomenon of over-squashing that causes poor performance for tasks relying on long-range interactions. T…
Transductive Kernels for Gaussian Processes on Graphs
Yin-Cong Zhi, Felix L. Opolka, Yin Cheng Ng +2
Kernels on graphs have had limited options for node-level problems. To address this, we present a novel, generalized kernel for graphs with node feature data for semi-supervised le…
Learning Hypergraphs From Signals With Dual Smoothness Prior
Bohan Tang, Siheng Chen, Xiaowen Dong
Hypergraph structure learning, which aims to learn the hypergraph structures from the observed signals to capture the intrinsic high-order relationships among the entities, becomes…
Unrolled Graph Learning for Multi-Agent Collaboration
Enpei Zhang, Shuo Tang, Xiaowen Dong +2
Multi-agent learning has gained increasing attention to tackle distributed machine learning scenarios under constrictions of data exchanging. However, existing multi-agent learning…
Learning to Infer Structures of Network Games
Emanuele Rossi, Federico Monti, Yan Leng +2
Strategic interactions between a group of individuals or organisations can be modelled as games played on networks, where a player's payoff depends not only on their actions but al…
Local2Global: A distributed approach for scaling representation learning on graphs
Lucas G. S. Jeub, Giovanni Colavizza, Xiaowen Dong +2
We propose a decentralised "local2global"' approach to graph representation learning, that one can a-priori use to scale any embedding technique. Our local2global approach proceeds…
On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
Emanuele Rossi, Henry Kenlay, Maria I. Gorinova +3
While Graph Neural Networks (GNNs) have recently become the de facto standard for modeling relational data, they impose a strong assumption on the availability of the node or edge…
Beltrami Flow and Neural Diffusion on Graphs
Benjamin Paul Chamberlain, James Rowbottom, Davide Eynard +3
We propose a novel class of graph neural networks based on the discretised Beltrami flow, a non-Euclidean diffusion PDE. In our model, node features are supplemented with positiona…
Adaptive Gaussian Processes on Graphs via Spectral Graph Wavelets
Felix L. Opolka, Yin-Cong Zhi, Pietro Liò +1
Graph-based models require aggregating information in the graph from neighbourhoods of different sizes. In particular, when the data exhibit varying levels of smoothness on the gra…
Local2Global: Scaling global representation learning on graphs via local training
Lucas G. S. Jeub, Giovanni Colavizza, Xiaowen Dong +2
We propose a decentralised "local2global" approach to graph representation learning, that one can a-priori use to scale any embedding technique. Our local2global approach proceeds…
Interpretable Stability Bounds for Spectral Graph Filters
Henry Kenlay, Dorina Thanou, Xiaowen Dong
Graph-structured data arise in a variety of real-world context ranging from sensor and transportation to biological and social networks. As a ubiquitous tool to process graph-struc…
On the Stability of Graph Convolutional Neural Networks under Edge Rewiring
Henry Kenlay, Dorina Thanou, Xiaowen Dong
Graph neural networks are experiencing a surge of popularity within the machine learning community due to their ability to adapt to non-Euclidean domains and instil inductive biase…
Graph signal processing for machine learning: A review and new perspectives
Xiaowen Dong, Dorina Thanou, Laura Toni +2
The effective representation, processing, analysis, and visualization of large-scale structured data, especially those related to complex domains such as networks and graphs, are o…
Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels
Binxin Ru, Xingchen Wan, Xiaowen Dong +1
Current neural architecture search (NAS) strategies focus only on finding a single, good, architecture. They offer little insight into why a specific network is performing well, or…
Gaussian Processes on Graphs via Spectral Kernel Learning
Yin-Cong Zhi, Yin Cheng Ng, Xiaowen Dong
We propose a graph spectrum-based Gaussian process for prediction of signals defined on nodes of the graph. The model is designed to capture various graph signal structures through…
Laplacian-regularized graph bandits: Algorithms and theoretical analysis
Kaige Yang, Xiaowen Dong, Laura Toni
We consider a stochastic linear bandit problem with multiple users, where the relationship between users is captured by an underlying graph and user preferences are represented as…
Error Analysis on Graph Laplacian Regularized Estimator
Kaige Yang, Xiaowen Dong, Laura Toni
We provide a theoretical analysis of the representation learning problem aimed at learning the latent variables (design matrix) of observations with the knowledge of the co…
Learning graphs from data: A signal representation perspective
Xiaowen Dong, Dorina Thanou, Michael Rabbat +1
The construction of a meaningful graph topology plays a crucial role in the effective representation, processing, analysis and visualization of structured data. When a natural choi…
Learning heat diffusion graphs
Dorina Thanou, Xiaowen Dong, Daniel Kressner +1
Effective information analysis generally boils down to properly identifying the structure or geometry of the data, which is often represented by a graph. In some applications, this…
Learning Laplacian Matrix in Smooth Graph Signal Representations
Xiaowen Dong, Dorina Thanou, Pascal Frossard +1
The construction of a meaningful graph plays a crucial role in the success of many graph-based representations and algorithms for handling structured data, especially in the emergi…