Your AI Papers Research Assistant

Today's Graph Neural Networks Research Top Papers

Wednesday, November 5, 2025
Proposes a Graph Neural Network (GNN) approach for human simulation, matching or surpassing LLM baselines on choice-among-discrete-options tasks. Demonstrates GNNs can be orders of magnitude smaller than LLMs while achieving comparable performance.
Proposes a GNN-based approach for Handwritten Mathematical Expression recognition by modeling expressions as graphs. Uses a deep BLSTM for initial graph formation, refined by GNN link prediction for structure recognition.
Combines causal inference with graph neural networks to address brittleness and discrimination in healthcare AI. Aims to learn causal mechanisms rather than just statistical associations for improved reliability and interpretability.
Utilizes Graph Neural Networks to predict interspecies interactions in microbial communities using monoculture growth capabilities, interactions, and phylogeny data. Aims to capture critical factors for community structure and activity.
Develops secure inference protocols for Graph Neural Networks (GNNs) and graph-structured data in privacy-critical environments. Addresses the underexplored challenge of securing GNNs, focusing on high-performance protocols.
Proposes an influence-aware causal autoencoder network for node importance ranking in complex networks. Aims to design node importance without direct reliance on network topology, addressing privacy concerns and improving generalization.
Derives insights from user text descriptions to build a federated recommendation system based on graph structures. Addresses data localization challenges in federated learning by capturing global user relationships.
Introduces a novel dynamic variational graph model for link prediction in global food trade networks. Captures temporal patterns using momentum structural memory and Bayesian optimization to model evolving network structures.
Sort by:
arxiv_cl

Link prediction Graph Neural Networks for structure recognition of Handwritten Mathematical Expressions

Abstract: Abstract: We propose a Graph Neural Network (GNN)-based approach for Handwritten Mathematical Expression (HME) recognition by modeling HMEs as graphs, where nodes represent symbols and edges capture spatial dependencies. A deep BLSTM network is used ...
#Graph Neural Networks#Pattern Recognition#Document Analysis#Symbol Recognition#Structural Analysis
17 hours ago
90%
arxiv_cl

Rethinking LLM Human Simulation: When a Graph is What You Need

Abstract: Abstract: Large language models (LLMs) are increasingly used to simulate humans, with applications ranging from survey prediction to decision-making. However, are LLMs strictly necessary, or can smaller, domain-grounded models suffice? We identify a ...
#Graph Neural Networks#Human Behavior Modeling#Agent-Based Simulation#LLM Alternatives#Decision Making
17 hours ago
92%
arxiv_ml

Unsupervised Evolutionary Cell Type Matching via Entropy-Minimized Optimal Transport

Abstract: Abstract: Identifying evolutionary correspondences between cell types across species is a fundamental challenge in comparative genomics and evolutionary biology. Existing approaches often rely on either reference-based matching, which imposes asymmet...
#Computational Biology#Genomics#Evolutionary Biology#Machine Learning#Graph Theory#Optimization
17 hours ago
85%
arxiv_ml

PrivGNN: High-Performance Secure Inference for Cryptographic Graph Neural Networks

Abstract: Abstract: Graph neural networks (GNNs) are powerful tools for analyzing and learning from graph-structured (GS) data, facilitating a wide range of services. Deploying such services in privacy-critical cloud environments necessitates the development o...
#Secure Machine Learning#Graph Analysis#Privacy in Cloud Computing#Cryptographic Techniques#Efficient Inference
17 hours ago
95%
arxiv_ml

Gradient GA: Gradient Genetic Algorithm for Drug Molecular Design

Abstract: Abstract: Molecular discovery has brought great benefits to the chemical industry. Various molecule design techniques are developed to identify molecules with desirable properties. Traditional optimization methods, such as genetic algorithms, continu...
#Molecular Design#Drug Discovery#Optimization Algorithms#Machine Learning
17 hours ago
95%
arxiv_ml

Effectiveness of High-Dimensional Distance Metrics on Solar Flare Time Series

Abstract: Abstract: Solar-flare forecasting has been extensively researched yet remains an open problem. In this paper, we investigate the contributions of elastic distance measures for detecting patterns in the solar-flare dataset, SWAN-SF. We employ a simple...
#Solar Physics#Time Series Analysis#Machine Learning#Clustering Algorithms#Data Mining
17 hours ago
50%
arxiv_ml

Addressing prior dependence in hierarchical Bayesian modeling for PTA data analysis II: Noise and SGWB inference through parameter decorrelation

Abstract: Abstract: Pulsar Timing Arrays provide a powerful framework to measure low-frequency gravitational waves, but accuracy and robustness of the results are challenged by complex noise processes that must be accurately modeled. Standard PTA analyses assi...
#Astrophysics#Gravitational Wave Detection#Statistical Modeling#Bayesian Inference#Signal Processing
17 hours ago
50%
arxiv_ml

Explainable Graph Neural Architecture Search via Monte-Carlo Tree Search (Full version)

Abstract: Abstract: The number of graph neural network (GNN) architectures has increased rapidly due to the growing adoption of graph analysis. Although we use GNNs in wide application scenarios, it is a laborious task to design/select optimal GNN architecture...
#Graph Neural Networks#Neural Architecture Search (NAS)#Machine Learning Interpretability#Graph Analysis#Algorithm Design
17 hours ago
95%
arxiv_ml

Learning CNF formulas from uniform random solutions in the local lemma regime

Abstract: Abstract: We study the problem of learning a $n$-variables $k$-CNF formula $\Phi$ from its i.i.d. uniform random solutions, which is equivalent to learning a Boolean Markov random field (MRF) with $k$-wise hard constraints. Revisiting Valiant's algor...
#Computational Learning Theory#Theoretical Computer Science#Satisfiability (SAT)#Machine Learning Theory#Boolean Functions
17 hours ago
85%
arxiv_ml

Relational Causal Discovery with Latent Confounders

Abstract: Abstract: Estimating causal effects from real-world relational data can be challenging when the underlying causal model and potential confounders are unknown. While several causal discovery algorithms exist for learning causal models with latent conf...
#Causal Inference#Causal Discovery#Graph Theory#Machine Learning#Relational Data Analysis
17 hours ago
90%
arxiv_ml

Data-driven Learning of Interaction Laws in Multispecies Particle Systems with Gaussian Processes: Convergence Theory and Applications

Abstract: Abstract: We develop a Gaussian process framework for learning interaction kernels in multi-species interacting particle systems from trajectory data. Such systems provide a canonical setting for multiscale modeling, where simple microscopic interact...
#Statistical Physics#Machine Learning#Bayesian Methods#Dynamical Systems#Scientific Computing
17 hours ago
85%
arxiv_ml

Are Foundational Atomistic Models Reliable for Finite-Temperature Molecular Dynamics?

Abstract: Abstract: Machine learning force fields have emerged as promising tools for molecular dynamics (MD) simulations, potentially offering quantum-mechanical accuracy with the efficiency of classical MD. Inspired by foundational large language models, rec...
#Computational Chemistry#Materials Science#Molecular Dynamics#Machine Learning for Science#Physics Simulation
17 hours ago
88%
arxiv_ml

Network Anomaly Traffic Detection via Multi-view Feature Fusion

Abstract: Abstract: Traditional anomalous traffic detection methods are based on single-view analysis, which has obvious limitations in dealing with complex attacks and encrypted communications. In this regard, we propose a Multi-view Feature Fusion (MuFF) met...
#Network Security#Machine Learning#Data Analysis#Cybersecurity#Anomaly Detection
17 hours ago
50%
arxiv_ml

Redundancy Maximization as a Principle of Associative Memory Learning

Abstract: Abstract: Associative memory, traditionally modeled by Hopfield networks, enables the retrieval of previously stored patterns from partial or noisy cues. Yet, the local computational principles which are required to enable this function remain incomp...
#Computational Neuroscience#Machine Learning Theory#Information Theory#Memory Systems#Neural Networks
17 hours ago
85%
arxiv_ml

Lower-dimensional projections of cellular expression improves cell type classification from single-cell RNA sequencing

Abstract: Abstract: Single-cell RNA sequencing (scRNA-seq) enables the study of cellular diversity at single cell level. It provides a global view of cell-type specification during the onset of biological mechanisms such as developmental processes and human or...
#Single-Cell Genomics#Bioinformatics#Machine Learning for Biology#Dimensionality Reduction#Cell Type Classification
17 hours ago
80%
arxiv_ml

Arithmetic Circuits and Neural Networks for Regular Matroids

Abstract: Abstract: We prove that there exist uniform $(+,\times,/)$-circuits of size $O(n^3)$ to compute the basis generating polynomial of regular matroids on $n$ elements. By tropicalization, this implies that there exist uniform $(\max,+,-)$-circuits and R...
#Combinatorial Optimization#Theoretical Computer Science#Graph Theory#Machine Learning Theory#Linear Programming
17 hours ago
88%
arxiv_ml

Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounders

Abstract: Abstract: Gene regulatory network inference (GRNI) aims to discover how genes causally regulate each other from gene expression data. It is well-known that statistical dependencies in observed data do not necessarily imply causation, as spurious depe...
#Causal Inference#Systems Biology#Bioinformatics#Gene Regulatory Networks#Statistical Modeling
17 hours ago
75%
arxiv_ml

UFGraphFR: Graph Federation Recommendation System based on User Text description features

Abstract: Abstract: Federated learning offers a privacy-preserving framework for recommendation systems by enabling local data processing; however, data localization introduces substantial obstacles. Traditional federated recommendation approaches treat each u...
#Federated Learning#Recommender Systems#Graph Neural Networks#Privacy-Preserving Machine Learning#Natural Language Processing
17 hours ago
90%
arxiv_ml

Delta-learned force fields for nonbonded interactions: Addressing the strength mismatch between covalent-nonbonded interaction for global models

Abstract: Abstract: Noncovalent interactions--vdW dispersion, hydrogen/halogen bonding, ion-$\pi$, and $\pi$-stacking--govern structure, dynamics, and emergent phenomena in materials and molecular systems, yet accurately learning them alongside covalent forces...
#Molecular Dynamics#Machine Learning for Chemistry#Force Fields#Computational Chemistry#Materials Science
17 hours ago
95%
arxiv_ml

Link Prediction with Untrained Message Passing Layers

Abstract: Abstract: Message passing neural networks (MPNNs) operate on graphs by exchanging information between neigbouring nodes. MPNNs have been successfully applied to various node-, edge-, and graph-level tasks in areas like molecular science, computer vis...
#Graph Neural Networks#Machine Learning#Network Analysis#Representation Learning#Algorithm Design
17 hours ago
95%
arxiv_ai

Efficient Vector Symbolic Architectures from Histogram Recovery

Abstract: Abstract: Vector symbolic architectures (VSAs) are a family of information representation techniques which enable composition, i.e., creating complex information structures from atomic vectors via binding and superposition, and have recently found wi...
#Information Representation#Coding Theory#Neurosymbolic AI#Artificial Intelligence#Signal Processing
17 hours ago
60%
arxiv_ml

Disentangling Causal Substructures for Interpretable and Generalizable Drug Synergy Prediction

Abstract: Abstract: Drug synergy prediction is a critical task in the development of effective combination therapies for complex diseases, including cancer. Although existing methods have shown promising results, they often operate as black-box predictors that...
#Drug Discovery#Causal Inference#Interpretable Machine Learning#Molecular Representation#Predictive Modeling
17 hours ago
90%
arxiv_ml

Causal Graph Neural Networks for Healthcare

Abstract: Abstract: Healthcare artificial intelligence systems routinely fail when deployed across institutions, with documented performance drops and perpetuation of discriminatory patterns embedded in historical data. This brittleness stems, in part, from le...
#Causal AI#Graph Neural Networks#Healthcare Applications#Fairness in AI#Robustness in AI
17 hours ago
95%
arxiv_ml

Probabilistic Graph Cuts

Abstract: Abstract: Probabilistic relaxations of graph cuts offer a differentiable alternative to spectral clustering, enabling end-to-end and online learning without eigendecompositions, yet prior work centered on RatioCut and lacked general guarantees and pr...
#Graph Theory#Clustering Algorithms#Differentiable Optimization#Machine Learning Theory#Representation Learning
17 hours ago
90%
arxiv_ml

Learning A Universal Crime Predictor with Knowledge-guided Hypernetworks

Abstract: Abstract: Predicting crimes in urban environments is crucial for public safety, yet existing prediction methods often struggle to align the knowledge across diverse cities that vary dramatically in data availability of specific crime types. We propos...
#Predictive Modeling#Urban Analytics#Knowledge Representation#Hypernetworks#Spatial-Temporal Data
17 hours ago
90%
arxiv_ml

SKGE: Spherical Knowledge Graph Embedding with Geometric Regularization

Abstract: Abstract: Knowledge graph embedding (KGE) has become a fundamental technique for representation learning on multi-relational data. Many seminal models, such as TransE, operate in an unbounded Euclidean space, which presents inherent limitations in mo...
#Knowledge Graphs#Representation Learning#Graph Embeddings#Geometric Deep Learning#Information Retrieval
17 hours ago
95%
arxiv_ml

COFAP: A Universal Framework for COFs Adsorption Prediction through Designed Multi-Modal Extraction and Cross-Modal Synergy

Abstract: Abstract: Covalent organic frameworks (COFs) are promising adsorbents for gas adsorption and separation, while identifying the optimal structures among their vast design space requires efficient high-throughput screening. Conventional machine-learnin...
#Predictive Modeling for Materials Science#Machine Learning for COF Design#Multi-modal Feature Learning#High-Throughput Screening of Adsorbents
17 hours ago
90%
arxiv_ml

Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments

Abstract: Abstract: Graph neural networks have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs. However, existing GNNs exhibit poor generalization ability under distribution shifts, which is inevitable in dynamic scen...
#Graph Neural Networks#Out-of-Distribution Generalization#Dynamic Systems#Causal Inference#Environment Modeling
17 hours ago
95%
arxiv_ml

Theoretical Guarantees for Causal Discovery on Large Random Graphs

Abstract: Abstract: We investigate theoretical guarantees for the false-negative rate (FNR) -- the fraction of true causal edges whose orientation is not recovered, under single-variable random interventions and an $\epsilon$-interventional faithfulness assump...
#Causal Inference#Graph Theory#Machine Learning Theory#Statistical Inference#Network Science
17 hours ago
80%
arxiv_ml

Predicting Microbial Interactions Using Graph Neural Networks

Abstract: Abstract: Predicting interspecies interactions is a key challenge in microbial ecology, as these interactions are critical to determining the structure and activity of microbial communities. In this work, we used data on monoculture growth capabiliti...
#Graph Neural Networks#Microbial Ecology#Systems Biology#Predictive Modeling#Network Analysis
17 hours ago
95%

Loading more papers...

📚 You've reached the end of the papers list