graph neural networks
PulseAugur coverage of graph neural networks — every cluster mentioning graph neural networks across labs, papers, and developer communities, ranked by signal.
- 2026-05-11 research_milestone A new method for pre-training GNNs using ECFPs shows improved performance in QSAR tasks. source
5 day(s) with sentiment data
-
Meshwatch: A GNN Fraud Detection Stack Built with MLOps
This article details the technical architecture and implementation of Meshwatch, a fraud detection system built using Graph Neural Networks (GNNs). It covers the entire MLOps lifecycle, from model training and infrastru…
-
UniGraphLM advances graph language models with cross-domain alignment
Researchers have introduced UniGraphLM, a novel Unified Graph Language Model designed to enhance the generalization capabilities of existing models. UniGraphLM addresses the challenge of aligning graph-encoded represent…
-
Random-Set GNNs enhance uncertainty quantification in graph learning
Researchers have introduced Random-Set Graph Neural Networks (RS-GNNs) to address uncertainty quantification in graph learning. This new framework models node-level epistemic uncertainty using a belief function formalis…
-
GNNs enhanced for drug discovery via ECFP pre-training
Researchers have developed a new strategy to enhance Graph Neural Networks (GNNs) for drug discovery tasks like Quantitative Structure-Activity Relationship (QSAR) studies. This method involves pre-training GNNs to pred…
-
New GRAPHLCP method enhances graph neural network uncertainty quantification
Researchers have introduced GRAPHLCP, a novel framework for structure-aware localized conformal prediction on graphs. This method addresses challenges in applying conformal prediction to graph neural networks by explici…
-
Bilevel graph learning gains attributed to training dynamics, not rewiring
Researchers have re-examined bilevel graph structure learning, a technique that jointly optimizes model parameters and graph structures to enhance graph neural networks. Their findings suggest that the performance gains…
-
Transfer learning boosts AI model efficiency in high-energy physics
Researchers have explored transfer learning techniques to improve machine learning model performance in high-energy physics. By pre-training models on computationally cheaper, fast-simulated data and then adapting them …
-
AI models learn traffic network behavior for faster simulations
Researchers have developed a new approach using machine learning, specifically Graph Neural Networks (GNNs), to address the traffic assignment problem (TAP). This method aims to predict traffic flow distribution across …
-
New ALDA4Rec method improves recommendation systems with graph-based learning
Researchers have developed a new method called ALDA4Rec to improve recommendation systems by addressing noise and static representations in graph-based models. The approach constructs an item-item graph, filters noise u…
-
GraphPI uses GNNs for efficient protein inference with pseudo-labels
Researchers have developed GraphPI, a new framework that frames protein inference as a node classification problem using Graph Neural Networks. This approach models proteins as interconnected nodes within a graph to und…
-
AI infers sensitive user data from music playlists, researchers develop defense
Researchers have developed a novel tool called musicPIIrate that uses deep learning to infer sensitive personal information from users' music playlists. The tool leverages set-based and graph neural network approaches t…
-
Ant Colony Optimization algorithm finds new life in graph neural networks
A 1992 algorithm inspired by ant colony behavior has resurfaced, demonstrating remarkable efficiency in solving complex problems. Initially developed from observations of Argentine ants, the Ant Colony Optimization (ACO…
-
Graph neural networks model gauge structures in lattice gauge theories
Researchers have developed a novel gauge-invariant graph neural network (GNN) architecture designed to handle Abelian lattice gauge models. This GNN explicitly enforces symmetry using local gauge-invariant inputs like W…
-
Researchers explore neural network complexity, computation, and graph theory connections
Researchers are exploring new theoretical frameworks and computational models for neural networks. One paper introduces a unified framework to analyze and construct deep neural networks by modeling tensor operations, re…
-
New framework U-CECE enhances AI explainability with multi-resolution concept analysis
Researchers have introduced U-CECE, a novel framework designed to enhance the explainability of complex AI models. This universal, multi-resolution system offers adaptable levels of conceptual counterfactual explanation…
-
New framework enhances AI simulations with spatial, temporal awareness
Researchers have developed a new framework to enhance machine learning models used for physics simulations, specifically addressing limitations in current training paradigms. Their approach introduces multi-node predict…
-
Graph Neural Networks accelerate VLSI design with faster capacitance modeling
Researchers have developed GNN-Ceff, a novel method utilizing Graph Neural Networks for post-layout effective capacitance modeling in VLSI design. This approach aims to improve the accuracy and speed of static timing an…
-
Researchers enhance financial NLP with opinion graphs for emotion analysis
Researchers have developed a method to semantically enrich investor micro-blogs for more nuanced emotion analysis in financial NLP. This approach augments the StockEmotions dataset with structured opinion graphs, provid…
-
DynoSLAM uses GNNs for safer robot navigation in crowded spaces
Researchers have developed DynoSLAM, a novel Dynamic GraphSLAM architecture that integrates Graph Neural Networks (GNNs) into factor graph optimization for improved robot navigation in crowded environments. This system …
-
LLMs struggle with graph structure, text alone suffices
A new study published on arXiv challenges the conventional wisdom that explicit graph structure is always beneficial for large language models (LLMs). Researchers found that LLMs perform surprisingly well on text-attrib…