4 papers
Clustering of Time-Varying Graphs Based on Temporal Label Smoothness
Katsuki Fukumoto, Koki Yamada, Yuichi Tanaka +1
We propose a node clustering method for time-varying graphs based on the assumption that the cluster labels are changed smoothly over time. Clustering is one of the fundamental tas…
Attention-based Graph Convolution Fusing Latent Structures and Multiple Features for Graph Neural Networks
Yang Li, Yuichi Tanaka
We present an attention-based spatial graph convolution (AGC) for graph neural networks (GNNs). Existing AGCs focus on only using node-wise features and utilizing one type of atten…
Directional Analytic Discrete Cosine Frames
Seisuke Kyochi, Taizo Suzuki, Yuichi Tanaka
Block frames called directional analytic discrete cosine frames (DADCFs) are proposed for sparse image representation. In contrast to conventional overlapped frames, the proposed D…
Structure-Aware Multi-Hop Graph Convolution for Graph Neural Networks
Yang Li, Yuichi Tanaka
In this paper, we propose a spatial graph convolution (GC) to classify signals on a graph. Existing GC methods are limited to using the structural information in the feature space.…