Rating Prediction via Graph Signal Processing

Huang, Wen; Marqués, Antonio G.; Ribeiro, Alejandro

doi:10.1109/tsp.2018.2864654

Cited by 67 publications

(100 citation statements)

References 37 publications

Supporting

Mentioning

100

Contrasting

Order By: Relevance

“…In the third experiment, we tackle the problem of predicting movie ratings using the MovieLens 100k dataset. In addition to comparing localized and pointwise activation functions, we contrast our performance with that of the recommendation systems proposed in [31] and [32]. The last experiment is a node classification task in which we use the Cora citation network and associated dataset to classify scientific articles into 7 different classes.…”

Section: B Computational Complexitymentioning

confidence: 99%

See 1 more Smart Citation

Invariance-Preserving Localized Activation Functions for Graph Neural Networks

Ruiz

Gama

Marqués

et al. 2020

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

Graph signals are signals with an irregular structure that can be described by a graph. Graph neural networks (GNNs) are information processing architectures tailored to these graph signals and made of stacked layers that compose graph convolutional filters with nonlinear activation functions. Graph convolutions endow GNNs with invariance to permutations of the graph nodes' labels. In this paper, we consider the design of trainable nonlinear activation functions that take into consideration the structure of the graph. This is accomplished by using graph median filters and graph max filters, which mimic linear graph convolutions and are shown to retain the permutation invariance of GNNs. We also discuss modifications to the backpropagation algorithm necessary to train local activation functions. The advantages of localized activation function architectures are demonstrated in four numerical experiments: source localization on synthetic graphs, authorship attribution of 19th century novels, movie recommender systems and scientific article classification. In all cases, localized activation functions are shown to improve model capacity.

show abstract

Section: B Computational Complexitymentioning

confidence: 99%

“…These have up to 3 filter taps that are also optimized on the training set. Because our methods look at each user/movie individually, to make for a fair comparison we test the method [31], multi-graph CNNs [32].…”

Section: Recommender Systemsmentioning

confidence: 99%

Invariance-Preserving Localized Activation Functions for Graph Neural Networks

Ruiz

Gama

Marqués

et al. 2020

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some studies combine the item and the user-based models [5]. Other studies have posed such similarity based collaborative filtering as a graph signal processing problem [6]; however the basic approach remains the same there in. Such techniques are simple to understand and analyze.…”

Section: Neighborhood / Similarity Based Modelsmentioning

confidence: 99%

Deep latent factor model for collaborative filtering

et al. 2020

View full text Add to dashboard Cite

Latent factor models have been used widely in collaborative filtering based recommender systems. In recent years, deep learning has been successful in solving a wide variety of machine learning problems. Motivated by the success of deep learning, we propose a deeper version of latent factor model. Experiments on benchmark datasets shows that our proposed technique significantly outperforms all stateof-the-art collaborative filtering techniques.

show abstract

“…In what follows, we consider the problem of movie recommendation systems [30]. We are given a dataset of user ratings for some movies, and we want to learn how a user would rate a specific movie given their previous ratings and all other users in the dataset.…”

Section: Rmse Differencementioning

confidence: 99%

Stability of Graph Neural Networks to Relative Perturbations

Gama

Ribeiro

Bruna

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Graph neural networks (GNNs), consisting of a cascade of layers applying a graph convolution followed by a pointwise nonlinearity, have become a powerful architecture to process signals supported on graphs. Graph convolutions (and thus, GNNs), rely heavily on knowledge of the graph for operation. However, in many practical cases the GSO is not known and needs to be estimated, or might change from training time to testing time. In this paper, we are set to study the effect that a change in the underlying graph topology that supports the signal has on the output of a GNN. We prove that graph convolutions with integral Lipschitz filters lead to GNNs whose output change is bounded by the size of the relative change in the topology. Furthermore, we leverage this result to show that the main reason for the success of GNNs is that they are stable architectures capable of discriminating features on high eigenvalues, which is a feat that cannot be achieved by linear graph filters (which are either stable or discriminative, but cannot be both). Finally, we comment on the use of this result to train GNNs with increased stability and run experiments on movie recommendation systems.

show abstract

Rating Prediction via Graph Signal Processing

Cited by 67 publications

References 37 publications

Invariance-Preserving Localized Activation Functions for Graph Neural Networks

Invariance-Preserving Localized Activation Functions for Graph Neural Networks

Deep latent factor model for collaborative filtering

Stability of Graph Neural Networks to Relative Perturbations

Contact Info

Product

Resources

About