A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification
[article]
2022
arXiv
pre-print
Graph neural networks (GNN) have been ubiquitous in graph node classification tasks. Most of GNN methods update the node embedding iteratively by aggregating its neighbors' information. ...
In this paper, we consider the label dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention. ...
THE PROPOSED METHOD In this section, we present the proposed Graph Decoupling Attention Markov Networks (GDAMNs) for semi-supervised graph node classification in detail. ...
arXiv:2104.13718v2
fatcat:c6lsicjpvzg4zgywiqujawwqqa
Semi-Supervised Hierarchical Graph Classification
[article]
2022
arXiv
pre-print
We study the node classification problem in the hierarchical graph where a 'node' is a graph instance. As labels are usually limited, we design a novel semi-supervised solution named SEAL-CI. ...
Node classification and graph classification are two graph learning problems that predict the class label of a node and the class label of a graph respectively. ...
This algorithm is called SEmi-supervised grAph cLassification (SEAL). ...
arXiv:2206.05416v1
fatcat:rsxjo4ztyng7lkh4nz6cozrmxm
Understanding and Improving Deep Graph Neural Networks: A Probabilistic Graphical Model Perspective
[article]
2023
arXiv
pre-print
Recently, graph-based models designed for downstream tasks have significantly advanced research on graph neural networks (GNNs). ...
Moreover, given this framework, more accurate approximations of FPE are brought, guiding us to design a more powerful GNN: coupling graph neural network (CoGNet). ...
Using GNN for semi-supervised node classification can be regarded as a marginal distribution estimation of latent variables on PGMs. ...
arXiv:2301.10536v1
fatcat:bnmxx34oezhqnfepi4dr4jleku
Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily
[article]
2022
arXiv
pre-print
Specifically, we first decouple the feature of each node into the discriminative feature for downstream tasks and the aggregation feature for graph convolution. ...
Due to the homophily assumption in graph convolution networks, a common consensus is that graph neural networks (GNNs) perform well on homophilic graphs but may fail on heterophilic graphs with many inter-class ...
INTRODUCTION Recently, emerging graph neural networks (GNNs) have demonstrated remarkable ability for semi-supervised node classification tasks. ...
arXiv:2203.11200v2
fatcat:g3i3qyabavhbtflp3xpbi4htry
A Scalable Deep Network for Graph Clustering via Personalized PageRank
2022
Applied Sciences
Recently, many models based on the combination of graph convolutional networks and deep learning have attracted extensive attention for their superior performance in graph clustering tasks. ...
Inspired by personalized pagerank and auto-encoder, we conduct the node-wise graph clustering task in the undirected simple graph as the research direction and propose a Scalable Deep Network (SDN) for ...
However, the above methods are suitable for supervised or semi-supervised learning scenarios, lacking a task-oriented model framework for unsupervised clustering tasks. ...
doi:10.3390/app12115502
fatcat:qhbodmkatvh4pjdekhpf6xhuqa
Graph Partner Neural Networks for Semi-Supervised Learning on Graphs
[article]
2021
arXiv
pre-print
Graph Convolutional Networks (GCNs) are powerful for processing graph-structured data and have achieved state-of-the-art performance in several tasks such as node classification, link prediction, and graph ...
However, it is inevitable for deep GCNs to suffer from an over-smoothing issue that the representations of nodes will tend to be indistinguishable after repeated graph convolution operations. ...
Experimental results show that GPNN outperforms the stateof-the-art baselines on various semi-supervised node classification tasks. ...
arXiv:2110.09182v1
fatcat:bhwivepnnbduvabeeyy7dhjw2y
Decoupling the Depth and Scope of Graph Neural Networks
[article]
2022
arXiv
pre-print
State-of-the-art Graph Neural Networks (GNNs) have limited scalability with respect to the graph and model sizes. ...
We propose a design principle to decouple the depth and scope of GNNs -- to generate representation of a target entity (i.e., a node or an edge), we first extract a localized subgraph as the bounded-size ...
Semi-supervised classification with graph convolutional
networks. arXiv preprint arXiv:1609.02907, 2016.
[23] Johannes Klicpera, Stefan Weißenberger, and Stephan Günnemann. ...
arXiv:2201.07858v1
fatcat:lzoilhqdrnbefntai4onjjoie4
Rethinking Node-wise Propagation for Large-scale Graph Learning
[article]
2024
arXiv
pre-print
Specifically, ATP has proven to be efficient in improving the performance of prevalent scalable GNNs for semi-supervised node classification while addressing redundant computational costs. ...
Scalable graph neural networks (GNNs) have emerged as a promising technique, which exhibits superior predictive performance and high running efficiency across numerous large-scale graph-based web applications ...
The semi-supervised node classification task is based on the topology of labeled set V 𝐿 and unlabeled set V 𝑈 , and the nodes in V 𝑈 are predicted with the model supervised by V 𝐿 .
1, GraphSAGE ...
arXiv:2402.06128v1
fatcat:cjyhtuk6png5bllzrnmpn7lixq
Local Augmentation for Graph Neural Networks
[article]
2022
arXiv
pre-print
Graph Neural Networks (GNNs) have achieved remarkable performance on graph-based tasks. ...
However, it remains an open question whether the neighborhood information is adequately aggregated for learning representations of nodes with few neighbors. ...
Specially, Songtao Liu is also thankful for the encouragement from Hao Yin. ...
arXiv:2109.03856v4
fatcat:6gtpa54jj5dsbg2mopndxfesq4
Out-Of-Distribution Generalization on Graphs: A Survey
[article]
2022
arXiv
pre-print
We also review the theories related to OOD generalization on graphs and introduce the commonly used graph datasets for thorough evaluations. ...
., data, model, and learning strategy, based on their positions in the graph machine learning pipeline, followed by detailed discussions for each category. ...
Machine learning approaches on graphs, especially for graph neural networks (GNNs), have attracted wide attention and been extensively studied in the last decade. ...
arXiv:2202.07987v2
fatcat:sngscwal4nhfbo6jtip74q2ume
Simple yet Effective Gradient-Free Graph Convolutional Networks
[article]
2023
arXiv
pre-print
Linearized Graph Neural Networks (GNNs) have attracted great attention in recent years for graph representation learning. ...
Compared with nonlinear Graph Neural Network (GNN) models, linearized GNNs are much more time-efficient and can achieve comparable performances on typical downstream tasks such as node classification. ...
In this paper, we focus on the semi-supervised node classification task [Welling and Kipf, 2016] . Under this scenario, each node is assigned to a label y i which represents a class c i . ...
arXiv:2302.00371v1
fatcat:j3yz32cnjrf4ln3r62gksfuai4
Effective Eigendecomposition based Graph Adaptation for Heterophilic Networks
[article]
2021
arXiv
pre-print
Graph Neural Networks (GNNs) exhibit excellent performance when graphs have strong homophily property, i.e. connected nodes have the same labels. However, they perform poorly on heterophilic graphs. ...
These adaptations are made either via attention or by attenuating or enhancing various low-frequency/high-frequency signals, as needed for the task at hand. ...
Graph Neural Networks (GNNs) [16, 13, 25] leverage network information along with node features to improve their semi-supervised classification performance. ...
arXiv:2107.13312v1
fatcat:dcn2oklm3ze5lmp5nrrqhohruq
Scalable Graph Neural Networks via Bidirectional Propagation
[article]
2021
arXiv
pre-print
Graph Neural Networks (GNN) is an emerging field for learning on non-Euclidean data. Recently, there has been increased interest in designing GNN that scales to large graphs. ...
Most notably, GBP can deliver superior performance on a graph with over 60 million nodes and 1.8 billion edges in less than half an hour on a single machine. ...
Transductive learning on small graphs. Table 4 shows the results for the semi-supervised transductive node classification task on the three small standard graphs Cora, Citeseer, and Pubmed. ...
arXiv:2010.15421v3
fatcat:bfyal2ha5vh5rot5z2s5q52t4m
Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
[article]
2020
arXiv
pre-print
Graph Neural Networks (GNNs) are the predominant technique for learning over graphs. ...
Here, we show that for many standard transductive node classification benchmarks, we can exceed or match the performance of state-of-the-art GNNs by combining shallow models that ignore the graph structure ...
In addition, we'd like to thank Matthias Fey and Marc Brockschmidt for insightful discussions. ...
arXiv:2010.13993v2
fatcat:7tnvv2aa6rb3jewabamr4ca6pm
Reinforcement learning on graphs: A survey
[article]
2023
arXiv
pre-print
Graph mining tasks arise from many different application domains, ranging from social networks, transportation to E-commerce, etc., which have been receiving great attention from the theoretical and algorithmic ...
As far as we know, this is the latest work on a comprehensive survey of GRL, this work provides a global view and a learning resource for scholars. ...
Collection Graph neural network Graph Reinforcement Learning Graph attention network Job Shop Scheduling Problem Long Short-Term Memory MDP Markov Decision Process γ Discount Factor. ...
arXiv:2204.06127v4
fatcat:xni47mpuijgohfhcpw5mwlqmya
« Previous
Showing results 1 — 15 out of 797 results