← Home

Daily arXiv Papers

Graph Neural Networks · Graph Learning · LLM × Graph

Showing 16 papers for 2026-04-30

A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication
GNN Graph Learning

This paper surveys multi-agent deep reinforcement learning approaches that rely on graph neural networks to enable inter-agent communication along interaction graphs. It discusses how GNN-based communication can enrich agents' representations and improve coordination. It also notes a lack of a unified framework to classify and distinguish MARL methods with graph-based communication.

Mini-Batch Class Composition Bias in Link Prediction
GNN Graph Learning

The authors show that, for a fixed graph, GNNs trained for link prediction do not generally learn representations that align with those learned for node classification. Instead, many models exploit a mini-batch dependent heuristic introduced by batch normalization to solve edge classification, which can hinder transferability.

Momentum-Conserving Graph Neural Networks for Deformable Objects
GNN Graph Learning

We introduce MomentumGNN, a graph neural network architecture designed to conserve momentum by construction, improving the accuracy of predicting the temporal evolution of linear and angular momentum in deformable-object dynamics. Unlike prior GNNs that output unconstrained accelerations, MomentumGNN enforces momentum constraints throughout the computation.

Unsupervised Graph Modeling for Anomaly Detection in Accounting Subject Relationships
GNN Graph Learning

The paper proposes an unsupervised graph-based framework for anomaly detection in accounting subject relationships. It models accounting subjects as graph nodes and encodes co-occurrence and debit/credit relationships as weighted edges to discover stable subject correspondences and detect structural deviations in ledgers and vouchers.

STLGT: A Scalable Trace-Based Linear Graph Transformer for Tail Latency Prediction in Microservices
Graph Learning

STLGT encodes traces as span graphs and uses a structure-aware linear graph transformer to forecast tail latency (p95) across multi-step service calls. It aims to capture long-range dependencies and non-stationary workloads with scalable inference for per-API tail-latency prediction.

PiGGO: Physics-Guided Learnable Graph Kalman Filters for Virtual Sensing of Nonlinear Dynamic Structures under Uncertainty
Graph Learning

PiGGO introduces Physics-Guided Learnable Graph Kalman Filters for virtual sensing of nonlinear dynamic structures under uncertainty. It combines physics-informed modeling, graph neural networks, and Bayesian state estimation to improve online state estimation under sparse sensing.

Sparse Graph Learning from Sparse Data via Fiedler Number Maximization
Graph Learning Graph Theory

We study sparse graph learning from sparse data by maximizing the Fiedler number as a robust regularizer to encourage connectivity. A greedy algorithm iteratively adds/removes a single edge to produce a sparse, connected graph from undersampled observations.

Efficient Traffic Forecasting on Large-Scale Road Network by Regularized Adaptive Graph Convolution
GNN Graph Learning

To scale STGCN to large road networks, the paper proposes a regularized adaptive graph convolution that reduces quadratic complexity while maintaining accurate spatial-temporal traffic forecasting. This approach enables efficient inference on large-scale networks.

Crime Hotspot Prediction Using Deep Graph Convolutional Networks
GNN Graph Learning

We propose a deep graph convolutional network framework for crime hotspot prediction that captures complex spatial dependencies among crime events. By modeling events on a graph, it addresses limitations of KDE and SVM approaches that treat spatial data as independent.

Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval
Knowledge Graph

ARK is an adaptive knowledge-graph retriever that gives a language model control over the breadth–depth tradeoff in retrieval. It enables efficient, multi-hop evidence gathering by balancing wide coverage with focused traversal.

PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework
Graph Learning

PACIFIER reframes opinion polarization moderation as a graph-based sequential planning task under Friedkin-Johnsen dynamics. It proposes a unified graph-learning framework to pace interventions for reducing polarization.

Probabilistic Graphical Model using Graph Neural Networks for Bayesian Inversion of Discrete Structural Component States
GNN Graph Learning

The paper presents a probabilistic graphical model built with graph neural networks for Bayesian inversion of discrete structural component states from measurements. It tackles ill-posedness by learning the likelihood and posterior in a data-driven, graph-based framework where the discrete states map to observed responses.

Deterministic Legal Agents: A Canonical Primitive API for Auditable Reasoning over Temporal Knowledge Graphs
Knowledge Graph

Deterministic Legal Agents proposes a canonical primitive API to enable auditable reasoning over temporal knowledge graphs for legal reasoning with LLMs. It provides structured interaction with structure-aware representations to preserve provenance and controllability.

PBiLoss: Popularity-Aware Regularization to Improve Fairness in Graph-Based Recommender Systems
Graph Learning

PBiLoss introduces a popularity-aware regularization to mitigate popularity bias in graph-based recommender systems. It improves fairness and diversity by balancing exposure across items.

Graph Propagated Projection Unlearning: A Unified Framework for Vision and Audio Discriminative Models
Graph Learning

Graph Propagated Projection Unlearning (GPPU) is a unified, scalable method for class-level unlearning that works across vision and audio models. It uses graph-based propagation to identify class-specific directions in feature space and projects representations onto an orthogonal subspace, followed by targeted fine-tuning.

CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering
Knowledge Graph LLM × Graph

CacheRAG presents a semantic caching system to augment Retrieval-Augmented Generation for Knowledge Graph Question Answering. It caches retrieval plans and prior evidence to improve retrieval consistency and reduce schema hallucinations, enabling more robust KGQA.