Understanding the Message Passing in Graph Neural Networks via Power Iteration Clustering

Li, Xue; Cheng, Yuanzhi

doi:10.48550/arxiv.2006.00144

Cited by 3 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering that the input of the MoRGH model is a heterogeneous graph, the process of message passing [45], which plays an important role in graph neural network learning, is different from homogeneous graphs and requires the notion of types. Types are crucial as different types have their own set of different data tensors in heterogeneous graphs.…”

Section: Graph Auto-encoder Creationmentioning

confidence: 99%

MoRGH: Movie Recommender System using GNNs on Heterogeneous Graphs

Ziaee,

Rahmani,

Nazari

2024

Preprint

View full text Add to dashboard Cite

Nowadays, with the advent of movies and TV shows and the competition between different movie streamer companies and movie databases to attract more users, movie recommenders have become a major prerequisite for customer satisfaction. Most of the previously introduced methods used collaborative, content-based, and hybrid filtering techniques, where neural network-based approaches, and matrix completion are the major approaches of most recent movie recommender systems. The major drawbacks of previous systems are not considering side information, cold start problem, and neglecting valuable information hidden when the data is presented in a heterogeneous graph like movie-movie or user-user information. In this paper, we propose a novel inductive approach called MoRGH which first constructs a graph of similar movies by considering the information available in movies’ plot synopsis and genres. Second, constructs a heterogeneous graph of users and movies by taking into account the movies’ rating information available in the Movielens dataset. Third, mitigates the drawbacks of previous methods by performing a GNN and GAE-based model to exploit a hybrid approach of collaborative and content-based approaches. Finally recommends, accurate and more personalized recommendations for each user, which outperforms previous state-of-the-art models w.r.t RMSE scores with an average of 0.1 based on movie ratings.

show abstract

Section: Graph Auto-encoder Creationmentioning

confidence: 99%

MoRGH: Movie Recommender System using GNNs on Heterogeneous Graphs

Ziaee,

Rahmani,

Nazari

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…MPNNs [47,14] have been used to predict the properties of molecules and materials [51,24,42,14,12,8,23,46,36,5,41,50,49,34], as well as to generate molecules and materials with desired properties [30,27]. There has been limited efforts in interpreting/explaining MPNNs or graph neural networks (GNNs) in general [46,28,17,22,25,52].…”

Section: Introductionmentioning

confidence: 99%

Towards explainable message passing networks for predicting carbon dioxide adsorption in metal-organic frameworks

Raza¹,

Faaiq²,

Sturluson³

et al. 2020

Preprint

View full text Add to dashboard Cite

Metal-organic framework (MOFs) are nanoporous materials that could be used to capture carbon dioxide from the exhaust gas of fossil fuel power plants to mitigate climate change. In this work, we design and train a message passing neural network (MPNN) to predict simulated CO 2 adsorption in MOFs. Towards providing insights into what substructures of the MOFs are important for the prediction, we introduce a soft attention mechanism into the readout function that quantifies the contributions of the node representations towards the graph representations. We investigate different mechanisms for sparse attention to ensure only the most relevant substructures are identified.

show abstract

“…To handle networks with node attributes, the field of graph neural networks (GNNs) has expanded rapidly in recent years [47][48][49][50]. Existing GNN models belong to the fam-ily of message passing frameworks [51,52], which update information for each node by recursively aggregating messages from its immediate neighbors in the graph. GNNs are generally classified into two categories, as follows.…”

mentioning

confidence: 99%

Fair Benchmark for Unsupervised Node Representation Learning

Guo

Chen²,

Huang³

et al. 2022

Algorithms

View full text Add to dashboard Cite

Most machine-learning algorithms assume that instances are independent of each other. This does not hold for networked data. Node representation learning (NRL) aims to learn low-dimensional vectors to represent nodes in a network, such that all actionable patterns in topological structures and side information can be preserved. The widespread availability of networked data, e.g., social media, biological networks, and traffic networks, along with plentiful applications, facilitate the development of NRL. However, it has become challenging for researchers and practitioners to track the state-of-the-art NRL algorithms, given that they were evaluated using different experimental settings and datasets. To this end, in this paper, we focus on unsupervised NRL and propose a fair and comprehensive evaluation framework to systematically evaluate state-of-the-art unsupervised NRL algorithms. We comprehensively evaluate each algorithm by applying it to three evaluation tasks, i.e., classification fine tuned via a validation set, link prediction fine-tuned in the first run, and classification fine tuned via link prediction. In each task and each dataset, all NRL algorithms were fine-tuned using a random search within a fixed amount of time. Based on the results for three tasks and eight datasets, we evaluate and rank thirteen unsupervised NRL algorithms.

show abstract

Understanding the Message Passing in Graph Neural Networks via Power Iteration Clustering

Cited by 3 publications

References 7 publications

MoRGH: Movie Recommender System using GNNs on Heterogeneous Graphs

MoRGH: Movie Recommender System using GNNs on Heterogeneous Graphs

Towards explainable message passing networks for predicting carbon dioxide adsorption in metal-organic frameworks

Fair Benchmark for Unsupervised Node Representation Learning

Contact Info

Product

Resources

About