#graph-analysis News & Analysis

6 articles tagged with #graph-analysis. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

6 articles

AI × CryptoBullisharXiv – CS AI · May 297/10

🤖

Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection

Researchers propose TEMG-TTA, a novel machine learning framework combining temporal motif analysis with test-time adaptation to improve anomaly detection on blockchain networks. The approach addresses critical challenges in detecting evolving fraudulent transaction patterns and out-of-distribution anomalies, demonstrating 54.88% performance improvement over existing graph-based detection methods across five real-world datasets.

AINeutralarXiv – CS AI · Jun 95/10

🧠

Rule-based autocorrection of Piping and Instrumentation Diagrams (P&IDs) on graphs

Researchers have developed a rule-based automated system to detect and correct errors in Piping and Instrumentation Diagrams (P&IDs), critical documents in chemical engineering. The method converts P&IDs into graph representations and applies 33 engineered rules to identify and fix mistakes, significantly reducing manual review workload for engineering projects involving hundreds or thousands of diagram pages.

AINeutralarXiv – CS AI · Jun 85/10

🧠

Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs

Researchers propose Label Context Classifier (LCC), a novel approach that enhances graph neural networks by capturing higher-order class label connectivity in heterophilous graphs where nodes with different labels tend to connect. The method integrates with existing GNNs and demonstrates superior performance on node classification tasks where traditional graph convolutional networks struggle.

AINeutralarXiv – CS AI · Jun 56/10

🧠

ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces

ReasoningFlow is a framework that maps the complex, non-linear reasoning traces of large reasoning models into directed acyclic graphs, enabling better understanding and monitoring of AI reasoning processes. Through analysis of 1,260 traces across multiple models and tasks, researchers discovered that LRMs exhibit structurally similar reasoning patterns despite different training origins, while most erroneous steps don't influence final answers.

AINeutralarXiv – CS AI · Mar 37/109

🧠

Property-Driven Evaluation of GNN Expressiveness at Scale: Datasets, Framework, and Study

Researchers developed a comprehensive evaluation framework for Graph Neural Networks (GNNs) using formal specification methods, creating 336 new datasets to test GNN expressiveness across 16 fundamental graph properties. The study reveals that no single pooling approach consistently performs well across all properties, with attention-based pooling excelling in generalization while second-order pooling provides better sensitivity.

AINeutralarXiv – CS AI · May 95/10

🧠

From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features

Researchers introduce a novel graph-based analysis method for sparse autoencoders (SAEs) in transformer models, using Weisfeiler-Lehman graph kernels to examine token co-occurrence patterns in SAE features. Applied to GPT-2 Small, this approach identifies structural motif families that traditional decoder weight analysis misses, revealing complementary insights into how neural networks organize semantic information.