IEEE Transactions on Neural Networks and Learning Systems

Diffusion models demonstrate strong potential for improving image quality and preserving fine-grained details in medical image fusion. However, the existing diffusion-based fusion methods lack modality-specific feature estimation during the iterative denoising process, resulting in the gradual entanglement of features. We propose a state-feedback optimization-based diffusion (STFO-Diff) framework…

In deep brain stimulation (DBS) surgery for Parkinson's disease (PD), the accurate intraoperative identification of key nuclei-such as the subthalamic nucleus (STN)-is critical to ensuring therapeutic efficacy. However, current approaches heavily depend on expert annotations, and classification tasks are typically confined to binary distinctions between STN and non-STN regions. This limitation ha…

Reinforcement learning (RL) has shown excellent performance in solving decision-making and control problems of autonomous driving (AD), which is increasingly applied in diverse driving scenarios. However, driving is a multiattribute problem, leading to challenges in achieving multiobjective compatibility for current RL methods, especially in both policy updating and policy execution. On the one h…

The end-to-end delay prediction is critical for intelligent network management, particularly in latency-sensitive and dynamic environments. While recent deep learning (DL) models have shown promising results, their reliance on sequential encoding of routing paths limits generalization to unseen routing schemes. In this article, we propose a robust graph neural network (GNN)-based delay prediction…

Continual learning (CL) aims to empower machine learning (ML) models to learn continually from new data, while building upon previously acquired knowledge without forgetting. As models have evolved from small to large pretrained architectures, and from supporting unimodal to multimodal (MM) data, multimodal CL (MMCL) methods have recently emerged. The primary complexity of MMCL is that it extends…

Composite resource allocation problems with general constraints are studied in this article, which frequently arise in networked systems such as smart grids and multiagent coordination. To address the challenges posed by multivalued differential inclusions resulting from nonsmooth objective functions, two anti-disturbance proximal neural networks are proposed, each tailored to handle structured a…

In real-world scenarios, random modality missingness in multimodal federated learning (mFL) poses a significant challenge, diminishing the performance of global model inference. However, existing mFL methods are predominantly limited to simple scenarios that typically involve participant clients restricted to either a single modality or multimodal clients with complete modalities. They employ mod…

The unsupervised open-set domain adaptation (UOSDA) in computer vision is widely studied. However, designing UOSDA algorithms for time series remains challenging due to the complex nonstationary property of data and distribution shifts across different operating conditions, which heighten the risk of negative transfer. To address this, a novel two-stage feature alignment (TSFA) method for UOSDA i…

Few-shot learning (FSL) enables deep learning models to generalize to unseen categories with minimal labeled data, making it crucial for data-constrained domains such as healthcare. However, existing FSL models often lack explainability, obscuring the reasoning behind their predictions and limiting trust in their deployment. In this work, we introduce contrastive cross-class attribution (C3A) to …

This article proposes and analyzes an accelerated reinforcement learning (RL) algorithm for discrete-time linear systems with unknown dynamics. The method achieves cubic convergence, improving upon the quadratic rates of existing policy iteration (PI)-based RL algorithms, and it does not rely on persistency of excitation (PE). The value function matrix is computed through a midpoint-centered Lyap…

The cooperative multiagent reinforcement learning (MARL) has been widely used in many practical applications. Despite its success, a fundamental issue arises in MARL that agents face the dilemma of whether to select the best action to maximize rewards or to acquire more information collectively by exploring the novel states/actions due to partial observability. To solve this issue, existing metho…

The Gaussian process (GP) is a powerful tool for nonparametric modeling, but its sensitivity to outliers limits its applicability to data distributions with heavy tails. Student-t processes (TPs) offer a robust alternative for heavy-tail modeling, but they lack the scalable developments of the GP to large datasets necessary for practical applications. We present sparse variational TPs (SVTPs), th…

Partial-label learning (PLL) studies classification with ambiguous supervision, where each instance is annotated by a candidate label set that contains the unknown true label. While PLL has been widely investigated, real-world annotation pipelines often provide richer structure than an unordered set: annotators or retrieval systems may implicitly rank candidates, yielding a preferred label that i…

Whilst spectral graph neural networks (GNNs) are theoretically well-founded in the spectral domain, their practical reliance on polynomial approximation implies a profound linkage to the spatial domain. As previous studies rarely examine spectral GNNs from the spatial perspective, their spatial-domain interpretability remains elusive, e.g., what information is essentially encoded by spectral GNNs…

RGB-depth underwater salient object detection (USOD) poses considerable challenges, such as uneven lighting, visual interference, and image blur, which limit the effectiveness of traditional approaches. The segment anything model (SAM), known for its robust segmentation capabilities, offers a promising alternative. However, SAM depends on prompt labels (e.g., points, boxes, and masks) to perform …

This article proposes stabilized model-based policy optimization (SMBPO) to address the stability and efficiency issues in current probabilistic model-based reinforcement learning (MBRL) approaches. It adaptively filters the noises caused by imperfect models in both model and policy updates: 1) dimensions with abnormal distributions in the prediction are refined to stabilize the training of proba…

Knowledge distillation (KD) aims to transfer knowledge from a cumbersome teacher to a lightweight student, thereby reducing overall model complexity without sacrificing performance. Current methods tend to focus excessively on pixel-level knowledge transfer while overlooking localized and contextual information. To address this, we propose a novel context-aware local region structural contrastive…

Nonconvex optimization presents significant challenges in many fields, particularly in training deep neural networks (DNNs), where poor local minima can degrade generalization-especially with limited data. High-dimensional nonconvex optimization presents two central challenges: 1) effectively balancing global exploration with rapid local exploitation and 2) establishing convergence guarantees, pa…

This article investigates a novel policy-adjustable Q-learning (PA-QL) algorithm aimed at addressing the optimal tracking control (OTC) problem for nonlinear discrete-time (DT) systems with enhanced adaptability and flexibility. A novel iteration scheme is developed that integrates the control weights into the augmented neural network (NN) input, thereby reformulating the learning process to expl…

Ensuring model fairness for preventing potential biases based on any sensitive attribute is crucial for the societal acceptance of artificial intelligence in critical applications. Among various fairness concepts, counterfactual fairness has gained prominence as it is grounded in causal inference. This concept requires that an individual's prediction in the original world remains consistent with …