Search Results for author:
Found 52 papers, 18 papers with code
Maximum Likelihood Estimation on Stochastic Blockmodels for Directed Graph Clustering
This paper studies the directed graph clustering problem through the lens of statistics, where we formulate clustering as estimating underlying communities in the directed stochastic block model (DSBM).
STEntConv: Predicting Disagreement with Stance Detection and a Signed Graph Convolutional Network
The rise of social media platforms has led to an increase in polarised online discussions, especially on political and socio-cultural topics such as elections and climate change.
Rough Transformers for Continuous and Efficient Time-Series Modelling
To mitigate this, we introduce the Rough Transformer, a variation of the Transformer model which operates on continuous-time representations of input sequences and incurs significantly reduced computational costs, critical for addressing long-range dependencies common in medical contexts.
Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning
In this paper, we propose DeLAMA, a decentralized multi-agent lifelong collaborative learning algorithm with dynamic collaboration graphs.
Hypergraph Node Classification With Graph Neural Networks
However, in this paper, we theoretically demonstrate that, in the context of node classification, most HyperGNNs can be approximated using a GNN with a weighted clique expansion of the hypergraph.
A Characterization Theorem for Equivariant Networks with Point-wise Activations
Equivariant neural networks have shown improved performance, expressiveness and sample complexity on symmetrical domains.
Hypergraph Transformer for Semi-Supervised Classification
Hypergraphs play a pivotal role in the modelling of data featuring higher-order relations involving more than two entities.
Hypergraph-MLP: Learning on Hypergraphs without Message Passing
Hypergraphs are vital in modelling data with higher-order relations containing more than two entities, gaining prominence in machine learning and signal processing.
Gromov-Hausdorff Distances for Comparing Product Manifolds of Model Spaces
Recent studies propose enhancing machine learning models by aligning the geometric characteristics of the latent space with the underlying data structure.
Hypergraph Structure Inference From Data Under Smoothness Prior
However, existing methods either adopt simple pre-defined rules that fail to precisely capture the distribution of the potential hypergraph structure, or learn a mapping between hypergraph structures and node features but require a large amount of labelled data, i. e., pre-existing hypergraph structures, for training.
Learning to Learn Financial Networks for Optimising Momentum Strategies
Network momentum provides a novel type of risk premium, which exploits the interconnections among assets in a financial network to predict future returns.
Network Momentum across Asset Classes
We investigate the concept of network momentum, a novel trading signal derived from momentum spillover across assets.
Wisdom of the Crowds or Ignorance of the Masses? A data-driven guide to WSB
Our initial experiments decompose the forum using a large language topic model and network tools.
Graph Neural Networks for Forecasting Multivariate Realized Volatility with Spillover Effects
We present a novel methodology for modeling and forecasting multivariate realized volatilities using customized graph neural networks to incorporate spillover effects across stocks.
On the Impact of Sample Size in Reconstructing Graph Signals
We show that under the setting of noisy observation and least-squares reconstruction this is not always the case, characterising the behaviour both theoretically and experimentally.
Structure-Aware Robustness Certificates for Graph Classification
Certifying the robustness of a graph-based machine learning model poses a critical challenge for safety.
Graph Classification Gaussian Processes via Spectral Features
Graph classification aims to categorise graphs based on their structure and node attributes.
DRew: Dynamically Rewired Message Passing with Delay
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.
Ranked #1 on
Graph Classification
on Peptides-func
Transductive Kernels for Gaussian Processes on Graphs
To address this, we present a novel, generalized kernel for graphs with node feature data for semi-supervised learning.
Learning Hypergraphs From Signals With Dual Smoothness Prior
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 crucial when a hypergraph topology is not readily available in the datasets.
Unrolled Graph Learning for Multi-Agent Collaboration
To fill this gap, we propose a distributed multi-agent learning model inspired by human collaboration, in which the agents can autonomously detect suitable collaborators and refer to collaborators' model for better performance.
Learning to Infer Structures of Network Games
We adopt a transformer-like architecture which correctly accounts for the symmetries of the problem and learns a mapping from the equilibrium actions to the network structure of the game without explicit knowledge of the utility function.
Graph similarity learning for change-point detection in dynamic networks
The main novelty of our method is to use a siamese graph neural network architecture for learning a data-driven graph similarity function, which allows to effectively compare the current graph and its recent history.
Local2Global: A distributed approach for scaling representation learning on graphs
Our local2global approach proceeds by first dividing the input graph into overlapping subgraphs (or "patches") and training local representations for each patch independently.
Adversarial Attacks on Graph Classifiers via Bayesian Optimisation
While the majority of the literature focuses on such vulnerability in node-level classification tasks, little effort has been dedicated to analysing adversarial attacks on graph-level classification, an important problem with numerous real-life applications such as biochemistry and social network analysis.
Understanding over-squashing and bottlenecks on graphs via curvature
Most graph neural networks (GNNs) use the message passing paradigm, in which node features are propagated on the input graph.
Ranked #43 on
Node Classification
on Citeseer
On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
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 features of the graph.
Adversarial Attacks on Graph Classification via Bayesian Optimisation
While the majority of the literature focuses on such vulnerability in node-level classification tasks, little effort has been dedicated to analysing adversarial attacks on graph-level classification, an important problem with numerous real-life applications such as biochemistry and social network analysis.
Adaptive Gaussian Processes on Graphs via Spectral Graph Wavelets
Graph-based models require aggregating information in the graph from neighbourhoods of different sizes.
Learning to Learn Graph Topologies
The model is trained in an end-to-end fashion with pairs of node data and graph samples.
Beltrami Flow and Neural Diffusion on Graphs
We propose a novel class of graph neural networks based on the discretised Beltrami flow, a non-Euclidean diffusion PDE.
Learning to Infer the Structure of Network Games
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 also on those of their neighbors.
Local2Global: Scaling global representation learning on graphs via local training
Our local2global approach proceeds by first dividing the input graph into overlapping subgraphs (or "patches") and training local representations for each patch independently.
Attacking Graph Classification via Bayesian Optimisation
Graph neural networks have been shown to be vulnerable to adversarial attacks.
Modeling Ideological Salience and Framing in Polarized Online Groups with Graph Neural Networks and Structured Sparsity
The increasing polarization of online political discourse calls for computational tools that automatically detect and monitor ideological divides in social media.
Interpretable Stability Bounds for Spectral Graph Filters
In this paper, we study filter stability and provide a novel and interpretable upper bound on the change of filter output, where the bound is expressed in terms of the endpoint degrees of the deleted and newly added edges, as well as the spatial proximity of those edges.
On the Stability of Graph Convolutional Neural Networks under Edge Rewiring
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 biases.
Interpretable Recommender System With Heterogeneous Information: A Geometric Deep Learning Perspective
Recommender systems (RS) are ubiquitous in the digital space.
Ranked #1 on
Recommendation Systems
on YahooMusic Monti
(using extra training data)
Kernel-based Graph Learning from Smooth Signals: A Functional Viewpoint
In this paper, we propose a novel graph learning framework that incorporates the node-side and observation-side information, and in particular the covariates that help to explain the dependency structures in graph signals.
Graph signal processing for machine learning: A review and new perspectives
The effective representation, processing, analysis, and visualization of large-scale structured data, especially those related to complex domains such as networks and graphs, are one of the key questions in modern machine learning.
Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels
Our method optimises the architecture in a highly data-efficient manner: it is capable of capturing the topological structures of the architectures and is scalable to large graphs, thus making the high-dimensional and graph-like search spaces amenable to BO.
Gaussian Processes on Graphs via Spectral Kernel Learning
We propose a graph spectrum-based Gaussian process for prediction of signals defined on nodes of the graph.
A Maximum Entropy approach to Massive Graph Spectra
Graph spectral techniques for measuring graph similarity, or for learning the cluster number, require kernel smoothing.
Laplacian-regularized graph bandits: Algorithms and theoretical analysis
In terms of network regret (sum of cumulative regret over $n$ users), the proposed algorithm leads to a scaling as $\tilde{\mathcal{O}}(\Psi d\sqrt{nT})$, which is a significant improvement over $\tilde{\mathcal{O}}(nd\sqrt{T})$ in the state-of-the-art algorithm \algo{Gob. Lin} \Ccite{cesa2013gang}.
Error Analysis on Graph Laplacian Regularized Estimator
We provide a theoretical analysis of the representation learning problem aimed at learning the latent variables (design matrix) $\Theta$ of observations $Y$ with the knowledge of the coefficient matrix $X$.
Learning Quadratic Games on Networks
Individuals, or organizations, cooperate with or compete against one another in a wide range of practical situations.
Learning graphs from data: A signal representation perspective
The construction of a meaningful graph topology plays a crucial role in the effective representation, processing, analysis and visualization of structured data.
Entropic Spectral Learning for Large-Scale Graphs
Graph spectra have been successfully used to classify network types, compute the similarity between graphs, and determine the number of communities in a network.
Learning heat diffusion graphs
Effective information analysis generally boils down to properly identifying the structure or geometry of the data, which is often represented by a graph.
Multi-modal image retrieval with random walk on multi-layer graphs
The analysis of large collections of image data is still a challenging problem due to the difficulty of capturing the true concepts in visual data.
Learning Laplacian Matrix in Smooth Graph Signal Representations
We show that the Gaussian prior leads to an efficient representation that favors the smoothness property of the graph signals.
Multiscale Event Detection in Social Media
In this paper, we propose a novel approach towards multiscale event detection using social media data, which takes into account different temporal and spatial scales of events in the data.
