Neural Networks最新文献

This paper addresses the consensus in fractional-order networked systems with matrix-weighted coupling, where the interactions of agents are characterized by positive definite or positive semi-definite matrices. A distributed sample-based control strategy is designed, in which each agent updates its state using sampled data. Some necessary and sufficient consensus conditions are derived for both undirected and directed matrix-weighted networks, respectively. The conditions depend on the sampling period, the fractional order, the control gain strengths, as well as the eigenvalue properties of the matrix-weighted Laplacian. Notably, for undirected networks, consensus is closely related to the null space of the matrix-weighted Laplacian. For directed networks, the existence of a positive spanning tree is not necessary to reach matrix-weighted consensus. Finally, simulation examples are conducted to validate the effectiveness of the theoretical analysis.

Pre-trained language models (PLMs) have achieved remarkable success across a wide range of natural language processing tasks, including text classification, machine translation, and question-answering systems, by leveraging vast amounts of unlabeled data to learn rich linguistic representations. However, existing models often reflect human-like biases and societal stereotypes, posing a significant challenge in their application. To address this issue, this paper proposes a novel debiasing framework called CFPLM. Unlike conventional debiasing methods, CFPLM is grounded in causal inference, aiming to identify and intervene in the factors that contribute to bias, thereby eliminating the bias in PLMs. The framework incorporates a composite loss function, which introduces a fairness penalty term to regulate the learning process of the model. Additionally, it integrates adversarial loss and entropy regularization to further optimize model performance. Experimental results demonstrate that, based on standard datasets and evaluation metrics, the proposed CFPLM method significantly reduces bias in BERT, RoBERTa, and ALBERT, while results on the GLUE benchmark indicate that enhancing model fairness does not compromise the models' language understanding capabilities.

Breast tumor images show low intra-class similarity and suffer from distribution shift, posing challenges for recognition tasks. While increasing the number of labeled training data is a common strategy to improve performance, the high cost of expert annotation is another challenge. Semi-supervised learning methods, e.g., Graph Neural Networks (GNNs), which smooth features via graph topology, have the potential to reduce the annotation costs for breast tumor datasets while achieving satisfactory classification performance. To address these challenges, we propose Graph Adiabatic Diffusion Neural Networks (GradiNet), which jointly learn discriminative graph structures for discriminative representation and simulate distribution shift environments. Specifically, we model the discriminative graph structure through a graph-learning objective function and demonstrate its effectiveness theoretically and empirically. Furthermore, we design a GNN feature propagation mechanism for the first time by incorporating the Fourier heat diffusion equation with adiabatic boundary conditions. Hence, the mechanism allows the model to adaptively simulate distribution shifts and enhance its generalization ability on both in-distribution (ID) and out-of-distribution (OOD) data. Extensive experiments on public and private breast tumor ultrasound image datasets demonstrate the superiority and effectiveness of our approach, achieving state-of-the-art performance across multiple evaluation metrics.

Safety and Restricted Communication are two critical challenges faced by practical Multi-Agent Systems (MAS). However, most Multi-Agent Reinforcement Learning (MARL) algorithms that rely solely on reward shaping are ineffective in ensuring safety, and their applicability is rather limited due to the fully connected communication. To address these issues, we propose a novel framework, Graph-based Safe MARL (GS-MARL), to enhance the safety and scalability of MARL methods. Leveraging the inherent graph structure of MAS, we design a Graph Neural Network (GNN) based on message passing to aggregate local observations and communications of varying sizes. Furthermore, we develop a constrained joint policy optimization method in the setting of local observation to improve safety. Simulation experiments demonstrate that GS-MARL achieves a better trade-off between optimality and safety compared to other methods, and in large-scale communication-limited scenarios GS-MARL achieves a success rate at least 10% higher than the leading baselines. The feasibility of our method is also verified by hardware implementation with Mecanum-wheeled vehicles. Codes and demos are available at https://github.com/finleygou/GS-MARL.