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.
Signed Graph Pre-Training and Prompt Learning
Related stories
arXiv Machine Learning
Aug 4
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.
arXiv Machine Learning
Jul 31
TopoFormer: Topology Meets Attention for Graph Learning
arXiv:2607. 28259v1 Announce Type: new Abstract: We introduce Topoformer, a lightweight and scalable framework for graph representation learning that encodes topological structure into attention-friendly sequences.
arXiv Machine Learning
Jun 16
Dynamic Link Prediction with Temporally Enhanced Signed Graph Neural Networks
arXiv:2605. 26290v2 Announce Type: replace Abstract: Temporal signed networks (TSNs) model the time evolution of cooperative and adversarial relationships that arise in applications such as social media analysis, trust and reputation systems, and financial transaction networks.
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 Machine Learning
Sep 10
Polarity-Asymmetric Structural Calibration for Link Sign Prediction
arXiv:2609.05896v1 Announce Type: cross Abstract: Link sign prediction (LSP) aims to infer the positive or negative polarity of unobserved links in signed networks. Signed Graph Neural Networks (SGNN...
Hugging Face Trending Papers
Sep 15
Repurposing Unified Topological Signatures for Graph Representation Learning
Message-passing Graph Neural Networks (GNNs) iteratively propagate and aggregate local neighborhood information followed by global readout to learn graph representations. However, their discriminative...
arXiv AI
Sep 16
Repurposing Unified Topological Signatures for Graph Representation Learning
arXiv:2609.17061v1 Announce Type: cross Abstract: Message-passing Graph Neural Networks (GNNs) iteratively propagate and aggregate local neighborhood information followed by global readout to learn g...
arXiv Machine Learning
Sep 10
Topology-induced Operators Reveal Complementary Graph Representations without Training
arXiv:2609.08152v1 Announce Type: new Abstract: Graph representation learning has largely focused on designing increasingly sophisticated models to transform graph topology into vector representation...
Hugging Face Trending Papers
Sep 8
Topology-induced Operators Reveal Complementary Graph Representations without Training
The paper demonstrates that high‑quality graph embeddings can be produced without complex models or training by propagating random features through topological structures derived from random walks and anonymous walks. These training‑free embeddings capture node proximity and structural roles, respectively, and perform competitively on node, edge, and graph tasks while often requiring less computation. Combining the two embedding types further improves inference quality for some tasks.
arXiv Machine Learning
Sep 3
From topology learning to graph generation: A unifying perspective
The article reviews the problem of learning graph structures from data, noting that research has traditionally split into two paths: inferring the topology of a single graph from observations on it, and learning a generative distribution from multiple observed graphs to sample new ones. It proposes a unified framework that treats both as inverse problems of a common graph generation process, reviews key methods, and discusses their interrelations, strengths, and limitations. The review highlights opportunities for cross‑paradigm integration and outlines future research directions.
arXiv AI
Jun 19
Protein Representation Learning with Secondary-Structure and Energy-Filtered Hydrogen-Bond Graphs
arXiv:2606. 19374v1 Announce Type: cross Abstract: Graph-based representations are widely used in protein modeling, yet many existing approaches rely primarily on sequence adjacency or geometric proximity, which only partially reflect the principles governing protein folding.