Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks

Graph Neural Networks (GNNs) have been widely used for the representation learning of various structured graph data, typically through message passing among nodes by aggregating their neighborhood information via different operations. While promising, most existing GNNs oversimplify the complexity and diversity of the edges in the graph and thus are inefficient to cope with ubiquitous heterogeneous graphs, which are typically in the form of multi-relational graph representations. In this article, we propose RioGNN , a novel Reinforced, recursive, and flexible neighborhood selection guided multi-relational Graph Neural Network architecture, to navigate complexity of neural network structures whilst maintaining relation-dependent representations. We first construct a multi-relational graph, according to the practical task, to reflect the heterogeneity of nodes, edges, attributes, and labels. To avoid the embedding over-assimilation among different types of nodes, we employ a label-aware neural similarity measure to ascertain the most similar neighbors based on node attributes. A reinforced relation-aware neighbor selection mechanism is developed to choose the most similar neighbors of a targeting node within a relation before aggregating all neighborhood information from different relations to obtain the eventual node embedding. Particularly, to improve the efficiency of neighbor selecting, we propose a new recursive and scalable reinforcement learning framework with estimable depth and width for different scales of multi-relational graphs. RioGNN can learn more discriminative node embedding with enhanced explainability due to the recognition of individual importance of each relation via the filtering threshold mechanism. Comprehensive experiments on real-world graph data and practical tasks demonstrate the advancements of effectiveness, efficiency, and the model explainability, as opposed to other comparative GNN models.

Distributed Cooperative Jamming with Neighborhood Selection Strategy for Unmanned Aerial Vehicle Swarms

In system science, a swarm possesses certain characteristics which the isolated parts and the sum do not have. In order to explore emergence mechanism of a large–scale electromagnetic agents (EAs), a neighborhood selection (NS) strategy–based electromagnetic agent cellular automata (EA–CA) model is proposed in this paper. The model describes the process of agent state transition, in which a neighbor with the smallest state difference in each sector area is selected for state transition. Meanwhile, the evolution rules of the traditional CA are improved, and performance of different evolution strategies are compared. An application scenario in which the emergence of multi–jammers suppresses the radar radiation source is designed to demonstrate the effect of the EA–CA model. Experimental results show that the convergence speed of NS strategy is better than those of the traditional CA evolution rules, and the system achieves effective jamming with the target after emergence. It verifies the effectiveness and prospects of the proposed model in the application of electronic countermeasures (ECM).

DNet: Dynamic Neighborhood Feature Learning in Point Cloud

Neighborhood selection is very important for local region feature learning in point cloud learning networks. Different neighborhood selection schemes may lead to quite different results for point cloud processing tasks. The existing point cloud learning networks mainly adopt the approach of customizing the neighborhood, without considering whether the selected neighborhood is reasonable or not. To solve this problem, this paper proposes a new point cloud learning network, denoted as Dynamic neighborhood Network (DNet), to dynamically select the neighborhood and learn the features of each point. The proposed DNet has a multi-head structure which has two important modules: the Feature Enhancement Layer (FELayer) and the masking mechanism. The FELayer enhances the manifold features of the point cloud, while the masking mechanism is used to remove the neighborhood points with low contribution. The DNet can learn the manifold features and spatial geometric features of point cloud, and obtain the relationship between each point and its effective neighborhood points through the masking mechanism, so that the dynamic neighborhood features of each point can be obtained. Experimental results on three public datasets demonstrate that compared with the state-of-the-art learning networks, the proposed DNet shows better superiority and competitiveness in point cloud processing task.

Integrating additional knowledge into the estimation of graphical models

Graphical models such as brain connectomes derived from functional magnetic resonance imaging (fMRI) data are considered a prime gateway to understanding network-type processes. We show, however, that standard methods for graphical modeling can fail to provide accurate graph recovery even with optimal tuning and large sample sizes. We attempt to solve this problem by leveraging information that is often readily available in practice but neglected, such as the spatial positions of the measurements. This information is incorporated into the tuning parameter of neighborhood selection, for example, in the form of pairwise distances. Our approach is computationally convenient and efficient, carries a clear Bayesian interpretation, and improves standard methods in terms of statistical stability. Applied to data about Alzheimer’s disease, our approach allows us to highlight the central role of lobes in the connectivity structure of the brain and to identify an increased connectivity within the cerebellum for Alzheimer’s patients compared to other subjects.