arXiv Machine Learning
Jul 31
MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian
arXiv:2209. 00546v5 Announce Type: replace-cross Abstract: Signed and directed networks are ubiquitous in real-world applications.
Nonlinear Laplacians Improve Signed-Directed Graph Learning
arXiv:2608. 00836v1 Announce Type: new Abstract: While signed-directed graphs have been studied using linear Laplacians in the design of graph neural networks, relatively little research has focused on developing non-linear Laplacian operators for such networks.
Related stories
arXiv Machine Learning
Jun 16
Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs
arXiv:2602. 10031v2 Announce Type: replace Abstract: Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral GNNs, reflecting two largely separate research traditions in machine learning and signal processing.
arXiv Machine Learning
Jun 19
Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
arXiv:2510. 16311v3 Announce Type: replace Abstract: Graph Contrastive Learning (GCL) has emerged as a powerful tool for extracting consistent representations from graphs, independent of labeled information.
arXiv AI
Aug 28
Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning
The paper reinterprets graph neural networks (GNNs) as retrieval-augmented models, where each layer uses an MLP on a node representation and a permutation‑invariant summary of retrieved graph context instead of traditional message passing. It introduces RTA, a lightweight MLP‑based framework that replaces structural message passing with label‑aware retrieval and propagation, and provides theoretical links to softmax‑attention message passing and robustness to mis‑retrieved outliers. Experiments on text‑attributed graph benchmarks demonstrate that RTA matches or surpasses strong GNN and graph LLM baselines while improving efficiency and robustness.
arXiv Machine Learning
Sep 2
Efficient Learning of Balanced Signed Graphs via Sparse Linear Programming
The paper introduces an efficient method for learning balanced signed graph Laplacians directly from data. By extending the CLIME sparse inverse covariance estimation framework, it formulates a linear programming problem for each Laplacian column with sign constraints that enforce positive edges between nodes of the same polarity and negative edges otherwise. The authors develop a tailored ADMM-based sparse LP solver, prove convergence properties, and demonstrate through experiments that the learned balanced graphs outperform existing methods and allow the reuse of spectral filtering tools, wavelets, and graph neural networks designed for positive graphs.
arXiv Machine Learning
Jun 10
Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing
arXiv:2606. 10284v1 Announce Type: new Abstract: Graph Contrastive Learning (GCL), which trains graph encoders by maximizing similarity between positive samples and minimizing it between negative ones, has emerged as a mainstream graph pre-training paradigm.
arXiv Machine Learning
Aug 26
TaLK: Text-attributed Graph Dataset Distillation via Coupling Language Model with Graph-Aware Kernel
arXiv:2606.22975v2 Announce Type: replace Abstract: Text-attributed graphs (TAGs) are widely used in many real-world domains, and learning on TAGs requires jointly modeling text semantics and graph s...
arXiv AI
Sep 1
Decoupled Structure-Feature Alignment via Alternating Optimization for Graph Learning
arXiv:2607.11577v2 Announce Type: replace-cross Abstract: Conventional Graph Neural Networks (GNNs) couple feature transformation and neighborhood aggregation, which often renders them vulnerable to...
arXiv Machine Learning
Sep 23
Signed Graph Pre-Training and Prompt Learning
arXiv:2609.25722v1 Announce Type: new Abstract: Signed graphs arise in trust--distrust networks, financial correlation systems, biological interaction graphs, and many other domains in which edges ca...
arXiv Machine Learning
Aug 27
DeltaGNN: Graph Neural Network with Information Flow Control
DeltaGNN introduces an information flow control mechanism that uses a new connectivity measure, the information flow score, to mitigate over‑smoothing and over‑squashing in Graph Neural Networks. This approach enables linear computational and memory overhead while effectively capturing both short‑range and long‑range node interactions. Experiments on ten diverse real‑world datasets demonstrate superior performance with limited computational complexity.
arXiv Machine Learning
Sep 15
Consistency of augmentation graph and network approximability in contrastive learning
arXiv:2502.04312v3 Announce Type: replace Abstract: Contrastive learning leverages data augmentation to develop feature representation without relying on large labeled datasets. However, despite its...
arXiv AI
Jul 14
Structure-Feature Aligned Graph Learning via Alternating Constrained Optimization
arXiv:2607. 11577v1 Announce Type: cross Abstract: We introduce a constrained two-view framework for node prediction that aligns structure-conditioned GNN embeddings with a structure-free feature prior learned by an anchor model.