Correlation-Aware Graph Convolutional Networks for Multi-Label Node Classification

Multi-label node classification is an important yet under-explored domain in graph mining as many real-world nodes belong to multiple categories rather than just a single one. Although a few efforts have been made by utilizing Graph Convolution Networks (GCNs) to learn node representations and model correlations between multiple labels in the embedding space, they still suffer from the ambiguous feature and ambiguous topology induced by multiple labels, which reduces the credibility of the messages delivered in graphs and overlooks the label correlations on graph data. Therefore, it is crucial to reduce the ambiguity and empower the GCNs for accurate classification. However, this is quite challenging due to the requirement of retaining the distinctiveness of each label while fully harnessing the correlation between labels simultaneously. To address these issues, in this paper, we propose a Correlation-aware Graph Convolutional Network (CorGCN) for multi-label node classification. By introducing a novel Correlation-Aware Graph Decomposition module, CorGCN can learn a graph that contains rich label-correlated information for each label. It then employs a Correlation-Enhanced Graph Convolution to model the relationships between labels during message passing to further bolster the classification process. Extensive experiments on five datasets demonstrate the effectiveness of our proposed CorGCN.

A Marginal Distributionally Robust Kalman Filter for Centralized Fusion

State estimation is a fundamental problem for multi-sensor information fusion, essential in applications such as target tracking, power systems, and control automation. Previous research mostly ignores the correlation between sensors and assumes independent or known distributions. However, in practice, these distributions are often correlated and difAcult to estimate. This paper proposes a novel moment constrained marginal distributionally robust Kalman Alter (MC-MDRKF) for centralized state estimation in multi-sensor systems. First, we introduce a marginal distributional uncertainty set using a moment-constrained approach, which can better capture the uncertainties of Gaussian noises compared to Kullback-Leibler (KL) divergence-based methods. Based on that, a minimax optimization problem is formulated to identify the least favorable joint distribution and the optimal MMSE estimator thereunder. It is proved that this problem can be reformulated as a convex optimization problem, allowing for efficient solution Anding. Subsequently, by accounting for marginal distributional uncertainty within the state space model, the proposed MC-MDRKF is devised in a minimax approach. Simulation result demonstrates the robustness and superiority of the proposed method in a multi-sensor target tracking scenario.