In this paper, we study the problem of learning Graph Convolutional Networks (GCNs) for regression. Current architectures of GCNs are limited to the small receptive field of convolution filters and shared transformation matrix for each node. To address these limitations, we propose Semantic Graph Convolutional Networks (SemGCN), a novel neural network architecture that operates on regression tasks with graph-structured data. SemGCN learns to capture semantic information such as local and global node relationships, which is not explicitly represented in the graph. These semantic relationships can be learned through end-to-end training from the ground truth without additional supervision or hand-crafted rules. We further investigate applying SemGCN to 3D human pose regression. Our formulation is intuitive and sufficient since both 2D and 3D human poses can be represented as a structured graph encoding the relationships between joints in the skeleton of a human body. We carry out comprehensive studies to validate our method. The results prove that SemGCN outperforms state of the art while using 90% fewer parameters. The code can be found at https://github.com/garyzhao/SemGCN .

We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training. We propose a new method named adversarial domain augmentation to solve this Outof-Distribution (OOD) generalization problem. The key idea is to leverage adversarial training to create "fictitious" yet "challenging" populations, from which a model can learn to generalize with theoretical guarantees. To facilitate fast and desirable domain augmentation, we cast the model training in a meta-learning scheme and use a Wasserstein Auto-Encoder (WAE) to relax the widely used worst-case constraint. Detailed theoretical analysis is provided to testify our formulation, while extensive experiments on multiple benchmark datasets indicate its superior performance in tackling single domain generalization.

Abstract-The escalating teletraffic growth imposed by the proliferation of smartphones and tablet computers outstrips the capacity increase of wireless communications networks. Furthermore, it results in substantially increased carbon dioxide emissions. As a powerful countermeasure, in the case of full-rank channel matrices, MIMO techniques are potentially capable of linearly increasing the capacity or decreasing the transmit power upon commensurately increasing the number of antennas. Hence, the recent concept of large-scale MIMO (LS-MIMO) systems has attracted substantial research attention and been regarded as a promising technique for next-generation wireless communications networks. Therefore, this paper surveys the state of the art of LS-MIMO systems. First, we discuss the measurement and modeling of LS-MIMO channels. Then, some typical application scenarios are classified and analyzed. Key techniques of both the physical and network layers are also detailed. Finally, we conclude with a range of challenges and future research topics.Index Terms-Large-scale MIMO, 3-D MIMO, channel modeling, physical layer, networking.

No abstract

No abstract