Many Graph Neural Networks (GNNs) are proposed for Knowledge Graph Embedding (KGE). However, lots of these methods neglect the importance of the information of relations and combine it with the information of entities inefficiently, leading to low expressiveness. To address this issue, we introduce a general knowledge graph encoder incorporating tensor decomposition in the aggregation function of Relational Graph Convolutional Network (R-GCN). In our model, neighbor entities are transformed using projection matrices of a low-rank tensor which are defined by relation types to benefit from multi-task learning and produce expressive relation-aware representations. Besides, we propose a low-rank estimation of the core tensor using CP decomposition to compress and regularize our model. We use a training method inspired by contrastive learning, which relieves the training limitation of the 1-N method on huge graphs. We achieve favorably competitive results on FB15k-237 and WN18RR with embeddings in comparably lower dimensions.

Originally published on Towards AI. The Graph Convolutional Network (GCN) is a revolutionary development in the field of deep learning, demonstrating its versatility and potential for application in addressing real-world problems. One such challenge is traffic prediction, which is a critical issue in transportation. The ability to adapt GCN algorithms for traffic prediction purposes holds immense promise and has the potential to significantly impact the transportation industry. It is important to note that this post assumes a prior understanding of GCN.

Graph convolutional networks (GCN) have been recently applied to semi-supervised classification problems with fewer labeled data and higher-dimensional features. Existing GCNs mostly rely on a first-order Chebyshev approximation of the graph wavelet-kernels. Such a generic propagation model may not always be well suited for the datasets. This work revisits the fundamentals of graph wavelet and explores the utility of spectral wavelet-kernels to signal propagation in the vertex domain. We first derive the conditions for representing the graph wavelet-kernels via vertex propagation. We next propose alternative propagation models for GCN layers based on Taylor expansions. We further analyze the choices of detailed propagation models. We test the proposed Taylor-based GCN (TGCN) in citation networks and 3D point clouds to demonstrate its advantages over traditional GCN methods.

The era of "data deluge" has sparked renewed interest in graph-based learning methods and their widespread applications ranging from sociology and biology to transportation and communications. In this context of graph-aware methods, the present paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that are represented by a tensor. Key aspects of the novel TGCN architecture are the dynamic adaptation to different relations in the tensor graph via learnable weights, and the consideration of graph-based regularizers to promote smoothness and alleviate over-parameterization. The ultimate goal is to design a powerful learning architecture able to: discover complex and highly nonlinear data associations, combine (and select) multiple types of relations, scale gracefully with the graph size, and remain robust to perturbations on the graph edges. The proposed architecture is relevant not only in applications where the nodes are naturally involved in different relations (e.g., a multi-relational graph capturing family, friendship and work relations in a social network), but also in robust learning setups where the graph entails a certain level of uncertainty, and the different tensor slabs correspond to different versions (realizations) of the nominal graph. Numerical tests showcase that the proposed architecture achieves markedly improved performance relative to standard GCNs, copes with state-of-the-art adversarial attacks, and leads to remarkable SSL performance over protein-to-protein interaction networks.

Cleveland Clinic is a non-profit academic medical center. Advertising on our site helps support our mission. Epilepsy is the second most common neurological disorder, impacting 1% to 2% of the world's population. Individuals with epilepsy typically undergo long-term monitoring of the brain's electrical activity with EEG recordings for several days. The recorded EEG data are manually reviewed by a trained neurologist, a neurophysiologist or a skilled EEG reader to identify epileptic seizures or interictal discharges that characterize the individual's epilepsy.

Seizure detection from EEGs is a challenging and time consuming clinical problem that would benefit from the development of automated algorithms. EEGs can be viewed as structural time series, because they are multivariate time series where the placement of leads on a patient's scalp provides prior information about the structure of interactions. Commonly used deep learning models for time series don't offer a way to leverage structural information, but this would be desirable in a model for structural time series. To address this challenge, we propose the temporal graph convolutional network (TGCN), a model that leverages structural information and has relatively few parameters. TGCNs apply feature extraction operations that are localized and shared over both time and space, thereby providing a useful inductive bias in tasks where one expects similar features to be discriminative across the different sequences. In our experiments we focus on metrics that are most important to seizure detection, and demonstrate that TGCN matches the performance of related models that have been shown to be state-of-the-art in other tasks. Additionally, we investigate interpretability advantages of TGCN by exploring approaches for helping clinicians determine when precisely seizures occur, and the parts of the brain that are most involved.