Results 71 to 80 of about 1,367 (116)
Flexible Diffusion Scopes with Parameterized Laplacian for Heterophilic Graph Learning
CoRRThe ability of Graph Neural Networks (GNNs) to capture long-range and global topology information is limited by the scope of conventional graph Laplacian, leading to unsatisfactory performance on some datasets, particularly on heterophilic graphs. To address this limitation, we propose a new class of parameterized Laplacian matrices, which provably ...
Qincheng Lu +3 more
openaire +3 more sources
THGNN: Temporal Heterophilic Graph Neural Network for Event-based Graph [PDF]
The present disclosure proposes techniques (e.g., a method and a system) for generating temporal heterophilic graph neural network (THGNN) for event-based graphs. All existing (temporal) GNNs typically follow temporal homophily assumption, while the real-
CHEN, HUIYUAN, Visa +4 more
core +1 more source
A polychromatic 'greenbeard' locus determines patterns of cooperation in a social amoeba [PDF]
, 2017 Cheaters disrupt cooperation by reaping the benefits without paying their fair share of associated costs. Cheater impact can be diminished if cooperators display a tag (‘greenbeard’) and recognise and preferentially direct cooperation towards other tag ...
Gruenheit, N +5 more
core
Adaptive Graph Learning with Node-Specific Aggregation [PDF]
Graph Neural Networks (GNNs) have shown remarkable performance in various graph-based tasks, but their effectiveness often diminishes when applied to heterophilic graphs, where connected nodes tend to have dissimilar features.
core +1 more source
HC-GST: Heterophily-aware Distribution Consistency based Graph Self-training
Graph self-training (GST), which selects and assigns pseudo-labels to unlabeled nodes, is popular for tackling label sparsity in graphs. However, recent study on homophily graphs show that GST methods could introduce and amplify distribution shift ...
Wang, Fali +3 more
core +1 more source
Unsupervised Graph Anomaly Detection via Multi-Hypersphere Heterophilic Graph Learning
CoRRGraph Anomaly Detection (GAD) plays a vital role in various data mining applications such as e-commerce fraud prevention and malicious user detection. Recently, Graph Neural Network (GNN) based approach has demonstrated great effectiveness in GAD by first encoding graph data into low-dimensional representations and then identifying anomalies under the ...
Hang Ni +3 more
openaire +2 more sources
Censoring Outdegree Compromises Inferences of Social Network Peer Effects and Autocorrelation [PDF]
, 2011 I examine the consequences of modelling contagious influence in a social network with incomplete edge information, namely in the situation where each individual may name a limited number of friends, so that extra outbound ties are censored. In particular,
Thomas, Andrew C.
core
Diversity and Popularity in Social Networks [PDF]
Homophily, the tendency of linked agents to have similar characteristics, is an important feature of social networks. We present a new model of network formation that allows the linking process to depend on individuals types and study the impact of such ...
Brian W. Rogers, Yann Bramoullé
core
Task-driven Heterophilic Graph Structure Learning
2025 59th Asilomar Conference on Signals, Systems, and ComputersGraph neural networks (GNNs) often struggle to learn discriminative node representations for heterophilic graphs, where connected nodes tend to have dissimilar labels and feature similarity provides weak structural cues. We propose frequency-guided graph structure learning (FgGSL), an end-to-end graph inference framework that jointly learns homophilic ...
Raghuvanshi, Ayushman +2 more
openaire +2 more sources
Beyond Homophily: Community Search on Heterophilic Graphs
Community search aims to identify a refined set of nodes that are most relevant to a given query, supporting tasks ranging from fraud detection to recommendation. Unlike homophilic graphs, many real-world networks are heterophilic, where edges predominantly connect dissimilar nodes.
Sima, Qing +2 more
openaire +2 more sources