Rethinking Graph Regularization for Graph Neural Networks
نویسندگان
چکیده
The graph Laplacian regularization term is usually used in semi-supervised representation learning to provide structure information for a model f(X). However, with the recent popularity of neural networks (GNNs), directly encoding A into model, i.e., f(A, X), has become more common approach. While we show that brings little-to-no benefit existing GNNs, and propose simple but non-trivial variant regularization, called Propagation-regularization (P-reg), boost performance GNN models. We formal analyses P-reg not only infuses extra (that captured by traditional regularization) also capacity equivalent an infinite-depth convolutional network. demonstrate can effectively models on both node-level graph-level tasks across many different datasets.
منابع مشابه
Kernel Graph Convolutional Neural Networks
Graph kernels have been successfully applied to many graph classification problems. Typically, a kernel is first designed, and then an SVM classifier is trained based on the features defined implicitly by this kernel. This two-stage approach decouples data representation from learning, which is suboptimal. On the other hand, Convolutional Neural Networks (CNNs) have the capability to learn thei...
متن کاملGated Graph Sequence Neural Networks
Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work on Graph Neural Networks (Scarselli et al., 2009), which we modify to use gated recurrent units and modern optimization techniques and then ex...
متن کاملNeural Networks and Graph Transformations
As the beginning of the area of artificial neural networks the introduction of the artificial neuron by McCulloch and Pitts is considered. They were inspired by the biological neuron. Since then many new networks or new algorithms for neural networks have been invented with the result. In most textbooks on (artificial) neural networks there is no general definition on what a neural net is but r...
متن کاملAdaptive Graph Convolutional Neural Networks
Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity. The paper proposes a generalized and flexible graph CNN taking dat...
متن کاملMIMO Graph Filters for Convolutional Neural Networks
Superior performance and ease of implementation have fostered the adoption of Convolutional Neural Networks (CNNs) for a wide array of inference and reconstruction tasks. CNNs implement three basic blocks: convolution, pooling and pointwise nonlinearity. Since the two first operations are welldefined only on regular-structured data such as audio or images, application of CNNs to contemporary da...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2021
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v35i5.16586