Robuta

https://www.amazon.science/publications/autogda-automated-graph-data-augmentation-for-node-classification AutoGDA: Automated graph data augmentation for node classification - Amazon Science Graph data augmentation has been used to improve generalizability of graph machine learning. However, by only applying fixed augmentation operations on entire... graph datanode classificationautomatedaugmentationamazon https://arxiv.org/abs/2405.20445 [2405.20445] Fully-inductive Node Classification on Arbitrary Graphs Abstract page for arXiv paper 2405.20445: Fully-inductive Node Classification on Arbitrary Graphs node classification2405fullyinductivearbitrary https://www.easychair.org/publications/preprint/GZFG Multi-Scale Directed Graph Convolution Neural Network for Node Classification Task convolution neural networkdirected graphnode classificationmultiscale https://openreview.net/forum?id=hESD2NJFg8 Label-free Node Classification on Graphs with Large Language Models (LLMs) | OpenReview In recent years, there have been remarkable advancements in node classification achieved by Graph Neural Networks (GNNs). However, they necessitate abundant... large language modelslabel freenode classification https://neo4j.com/docs/snowflake-graph-analytics/current/algorithms/graphsage/node-classification/training/ GraphSAGE node classification training - Neo4j Graph Analytics for Snowflake This section describes the GraphSAGE node classification training algorithm in Neo4j Graph Analytics for Snowflake. node classificationgraph analyticstrainingneo4jsnowflake https://openreview.net/forum?id=f_kvHrM4Q0&ref=graphusergroup.com Co-Modality Graph Contrastive Learning for Imbalanced Node Classification | OpenReview We design a co-modality graph contrastive learning model with network pruning to learn graph representations on imbalanced data. co modalitycontrastive learningnode classificationgraphimbalanced https://openreview.net/forum?id=3cL2XDyaEB EGonc : Energy-based Open-Set Node Classification with substitute Unknowns | OpenReview Open-set Classification (OSC) is a critical requirement for safely deploying machine learning models in the open world, which aims to classify samples from... energy basedopen setnode classification https://openreview.net/forum?id=FIs5yQMumUd A New Graph Node Classification Benchmark: Learning Structure from Histology Cell Graphs |... The paper presents a new node classification benchmark dataset: predicting micro-anatomical tissue structure from cell graphs in placenta histology, with the... a newgraph node https://openreview.net/forum?id=8wGXnjRLSy Zero-shot Node Classification with Graph Contrastive Embedding Network | OpenReview This paper studies zero-shot node classification, which aims to predict new classes (i.e., unseen classes) of nodes in a graph. This problem is challenging yet... zero shotnode classificationgraphcontrastiveembedding https://openreview.net/forum?id=CxUuCydMDU Diffusion Probabilistic Models for Structured Node Classification | OpenReview This paper studies structured node classification on graphs, where the predictions should consider dependencies between the node labels. In particular, we... probabilistic modelsnode classificationdiffusionstructuredopenreview https://openreview.net/forum?id=0gvtoxhvMY Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition |... This paper introduces a new approach to address the issue of class imbalance in graph neural networks (GNNs) for learning on graph-structured data. Our... node classificationbias variancerethinkingsemisupervised https://openreview.net/forum?id=w3x8K0M6sAz Topology-Imbalance Learning for Semi-Supervised Node Classification | OpenReview This paper study a graph-specific imbalance issue: topology imbalance and the relative solution. node classificationtopologyimbalancelearningsemi https://openreview.net/forum?id=0gvtoxhvMY¬eId=bBcG4XGOE8 Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition |... This paper introduces a new approach to address the issue of class imbalance in graph neural networks (GNNs) for learning on graph-structured data. Our... node classificationbias variancerethinkingsemisupervised https://openreview.net/forum?id=N0Pigj5tpHE Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification | OpenReview The interdependence between nodes in graphs is key to improve class prediction on nodes, utilized in approaches like Label Probagation (LP) or in Graph Neural... node classificationgraphposteriornetworkbayesian https://openreview.net/forum?id=MY2UroxLfJ Exploiting All Laplacian Eigenvectors for Node Classification with Graph Transformers | OpenReview Graph transformers have emerged as powerful tools for modeling complex graph-structured data, offering the ability to capture long-range dependencies. They... node classificationexploitinglaplacianeigenvectors https://openreview.net/forum?id=8KYeilT3Ow NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs | OpenReview We propose a novel Graph Transformer that utilizes the neighborhood aggregation of multiple hops to build the input sequence of token vectors and thereby can... https://openreview.net/forum?id=xlhDcKrTVF&referrer=%5Bthe%20profile%20of%20Jiaqi%20Zhu%5D(%2Fprofile%3Fid%3D~Jiaqi_Zhu1) When Do Graph Neural Networks Help with Node Classification: Investigating the Homophily Principle... Homophily principle, i.e. nodes with the same labels are more likely to be connected, has been believed to be the main reason for the performance superiority... graph neural networks https://openreview.net/forum?id=2EhGTwqwX2 DeCaf: A Causal Decoupling Framework for OOD Generalization on Node Classification | OpenReview Graph Neural Networks (GNNs) are susceptible to distribution shifts, creating vulnerability and security issues in critical domains. There is a pressing need...