1,721,007 research outputs found
Learning deep fair graph neural networks
No full textDeveloping learning methods which do not discriminate subgroups in the population is the central goal of algorithmic fairness. One way to reach this goal is to learn a data representation that is expressive enough to describe the data and fair enough to remove the possibility to discriminate subgroups when a model is learned leveraging on the learned representation. This problem is even more challenging when our data are graphs, which nowadays are ubiquitous and allow to model entities and relationships between them. In this work we measure fairness according to demographic parity, requiring the probability of the possible model decisions to be independent of the sensitive information. We investigate how to impose this constraint in the different layers of a deep graph neural network through the use of two different regularizers. The first one is based on a simple convex relaxation, and the second one inspired by a Wasserstein distance formulation of demographic parity. We present experiments on a real world dataset, showing the effectiveness of our proposal
On Filter Size in Graph Convolutional Networks
No full textRecently, many researchers have been focusing on the definition of neural networks for graphs. The basic component for many of these approaches remains the graph convolution idea proposed almost a decade ago. In this paper, we extend this basic component, following an intuition derived from the well-known convolutional filters over multi-dimensional tensors. In particular, we derive a simple, efficient and effective way to introduce a hyper-parameter on graph convolutions that influences the filter size, i.e. its receptive field over the considered graph. We show with experimental results on real-world graph datasets that the proposed graph convolutional filter improves the predictive performance of Deep Graph Convolutional Networks
Deep recurrent graph neural networks
Full text linkGraph Neural Networks (GNN) show good results in classification and regression on graphs, notwithstanding most GNN models use a limited depth. In fact, they are composed of only a few stacked graph convolutional layers. One reason for this is the number of parameters growing with the number of GNN layers. In this paper, we show how using a recurrent graph convolution layer can help in building deeper GNNs, without increasing the complexity of the training phase, while improving on the predictive performances. We also analyze how the depth of the model influences the final result
A framework for the definition of complex structured feature spaces
No full textIn this paper, we propose a general framework that, starting from the feature space of an existing base graph kernel, allows to define more expressive kernels which can learn more complex concepts, meanwhile generalizing different proposals in literature. Experimental results on eight real-world graph datasets from different domains show that the proposed framework instances are able to get a statistically significant performance improvement over both the considered base kernels and framework instances previously defined in literature, obtaining state-of-the-art results on all the considered datasets
Simple Multi-resolution Gated GNN
No full textMost Graph Neural Networks (GNNs) proposed in literature tend to add complexity (and non-linearity) to the model. In this paper, we follow the opposite direction by proposing a simple linear multi-resolution architecture that implements a multi-head gating mechanism. We assessed the performances of the proposed architecture on node classification tasks. To perform a fair comparison and present significant results, we re-implemented the competing methods from the literature and ran the experimental evaluation considering two different experimental settings with different model selection procedures. The proposed convolution, dubbed Simple Multi-resolution Gated GNN, exhibits state-of-the-art predictive performance on the considered benchmark datasets in terms of accuracy. In addition, it is way more efficient to compute than GAT, a well-known multihead GNN proposed in literature
Multiresolution Reservoir Graph Neural Network
No full textGraph neural networks are receiving increasing attention as state-of-the-art methods to process graph-structured data. However, similar to other neural networks, they tend to suffer from a high computational cost to perform training. Reservoir computing (RC) is an effective way to define neural networks that are very efficient to train, often obtaining comparable predictive performance with respect to the fully trained counterparts. Different proposals of reservoir graph neural networks have been proposed in the literature. However, their predictive performances are still slightly below the ones of fully trained graph neural networks on many benchmark datasets, arguably because of the oversmoothing problem that arises when iterating over the graph structure in the reservoir computation. In this work, we aim to reduce this gap defining a multiresolution reservoir graph neural network (MRGNN) inspired by graph spectral filtering. Instead of iterating on the nonlinearity in the reservoir and using a shallow readout function, we aim to generate an explicit k-hop unsupervised graph representation amenable for further, possibly nonlinear, processing. Experiments on several datasets from various application areas show that our approach is extremely fast and it achieves in most of the cases comparable or even higher results with respect to state-of-the-art approaches
A systematic assessment of deep learning models for molecule generation
Full text linkIn recent years the scientific community has devoted much effort in the development of deep learning models for the generation of new molecules with desirable properties (i.e. drugs). This has produced many proposals in literature. However, a systematic comparison among the different VAE methods is still missing. For this reason, we propose an extensive testbed for the evaluation of generative models for drug discovery, and we present the results obtained by many of the models proposed in literature
- …
