The rapid growth of publicly available data has fueled deep learning advancements but also raises concerns about unauthorized data usage. Unlearnable Examples (UEs) have emerged as a data protection strategy that introduces imperceptible perturbations to prevent unauthorized learning. However, most existing UE methods produce perturbations strongly tied to specific training sets, leading to a significant drop in unlearnability when applied to unseen data or tasks. In this paper, we argue that for broad applicability, UEs should maintain their effectiveness across diverse application scenarios. To this end, we conduct the first comprehensive study on the transferability of UEs across diverse and practical yet demanding settings. Specifically, we identify key scenarios that pose significant challenges for existing UE methods, including varying styles, out-of-distribution classes, resolutions, and architectures. Moreover, we propose $\textbf{Versatile Transferable Generator}$ (VTG), a transferable generator designed to safeguard data across various conditions. Specifically, VTG integrates Adversarial Domain Augmentation (ADA) into the generator’s training process to synthesize out-of-distribution samples, thereby improving its generalizability to unseen scenarios. Furthermore, we propose a Perturbation-Label Coupling (PLC) mechanism that leverages contrastive learning to directly align perturbations with class labels. This approach reduces the generator’s reliance on data semantics, allowing VTG to produce unlearnable perturbations in a distribution-agnostic manner. Extensive experiments demonstrate the effectiveness and broad applicability of our approach. Code is available at https://github.com/zhli-cs/VTG.

Steam, which plays an essential role in heat source medium for heating and cooling, is extensively utilized in industrial parks. Due to the high temperature and pressure characteristics of steam, which has the potential to cause damage to the steam pipeline easily. It is crucial to conduct fault diagnosis for the steam pipeline timely. This article is concerned with the active fault diagnosis (AFD) problem for the steam pipeline with multitime-scale properties. The global consensus AFD method based on the multitime-scale set-membership observer is proposed to solve the issue of inconsistent timescales, which not only achieves state estimation sets under different timescales but also guarantees the global consistency of fault diagnosis results. In view of the leakage fault modeling problem of the steam pipeline, a novel steam transportation model considering the leakage energy loss is established. Moreover, when establishing the optimization problem of the auxiliary signal, original inputs with dynamic characteristics are considered. The key of optimization problem comes down to the separation of healthy and faulty state estimation sets. Finally, experimental results are given to illustrate the effectiveness of the proposed AFD methodology with the steam pipeline data from a steel industrial park.

In the field of domain generalization, the task of constructing a predictive model capable of generalizing to a target domain without access to target data remains challenging. This problem becomes further complicated when considering evolving dynamics between domains. While various approaches have been proposed to address this issue, a comprehensive understanding of the underlying generalization theory is still lacking. In this study, we contribute novel theoretic results that aligning conditional distribution leads to the reduction of generalization bounds. Our analysis serves as a key motivation for solving the Temporal Domain Generalization (TDG) problem through the application of Koopman Neural Operators, resulting in Temporal Koopman Networks (TKNets). By employing Koopman Neural Operators, we effectively address the time-evolving distributions encountered in TDG using the principles of Koopman theory, where measurement functions are sought to establish linear transition relations between evolving domains. Through empirical evaluations conducted on synthetic and real-world datasets, we validate the effectiveness of our proposed approach.

As motor, electrical control, and battery technology progress, electric vehicles (EVs) are becoming increasingly prevalent. The electronic-electrical (EE) architecture of EVs has been refined, offering a fertile environment for developing intelligent connected vehicles. The integration of vehicles with technologies like big data and cloud platforms gave rise to the Internet of Vehicles (IoV), Vehicle-toEverything (V2X) communication technology, and the concept of Intelligent Connected Vehicles (ICVs). By investigating the technologies of ICVs and IoV, the development background, research status of V2X communication technology and cloud platform big data technology are presented in this study. It also analyzes the challenges of the current application of these technologies in the ICV and IoV and proposes technical solutions to the corresponding problems in light of the challenges. Furthermore, it looks forward to the future development of IoV technology and ICVs and puts forward personal suggestions.

With the advancement of system-on-chip (SOC) technology, automotive electronic control units (ECUs) have shifted from the distributed heterogeneous multiprocessor architecture to the centralized heterogeneous multicore processor architecture. This transformation provides a high-speed inter-core data exchange mechanism based on shared memory. In the distributed architectures, automotive communication software predominantly leverages the CAN bus for inter-core communication, which fundamentally differs from shared memory-based communication methods. This difference can cause significant porting difficulties when porting existing communication software to new hardware architectures. Balancing communication performance and porting efficiency has become a new challenge. To this end, we introduce a communication framework for CAN bus in heterogeneous multicore systems, namely—VirtCAN, which is optimized based on the mainstream heterogeneous multicore communication framework RPMsg. RPMsg is a lightweight inter-core communication framework for heterogeneous multicore systems based on shared memory. VirtCAN emulates the functions of actual CAN controllers by optimizing and encapsulating RPMsg. This approach preserves the original CAN communication method while enabling faster inter-core data exchange through shared memory, thereby achieving a balance between software porting efficiency and communication performance. Experiments were conducted on heterogeneous multicore processors based on ARM architecture, validating VirtCAN's significant communication advantages over the CAN bus and the original RPMsg.

High-performance domain controllers' hardware and software are put to the test by the growing array of additional capabilities found in smart, connected cars. In smart connected automobiles, the energy consumption of high-performance domain controllers is contributing to the whole vehicle's energy consumption at an increasing rate, even though hardware systems' computing capacity is also expanding quickly. Thus, it is crucial to research reducing processor energy consumption while maintaining system performance and dependability. This paper investigates the problem of energy-optimized task scheduling in an on-board operating system for SOA-oriented architectures by combining the DVFS technique and the DAG task model under the constraints of scheduling duration and reliability. Firstly, the energy-optimal task scheduling problem for heterogeneous multicore systems is described, focusing on the constraints of scheduling duration and reliability. The shortcomings of traditional task scheduling algorithms are also analyzed. Secondly, a task scheduling algorithm based on the meta-heuristic Whale Optimization Algorithm (WOA) is proposed. This algorithm includes the design of encoding, decoding, and constraint processing schemes, and assigns processing units and corresponding DVFS levels to each task in the DAG task set to achieve energy consumption optimization while satisfying constraints. To address the suboptimal performance of the Whale Optimization Algorithm in high-dimensional problems, a multi-strategy optimization approach is introduced. This enhanced algorithm incorporates chaotic mapping, adaptive nonlinear convergence factors, dynamic inertia coefficients, the Lévy flight strategy, and the evolutionary population dynamics strategy. Finally, the effectiveness of the proposed algorithm is validated through simulation experiments.

Semantic segmentation is a critical component of autonomous driving perception systems and has gained increasing attention in recent advancements. Autonomous vehicles frequently encounter diverse environmental conditions, highlighting the significance of research into domain adaptation for semantic segmentation. We established a domain adversarial framework for enhancing the cross-domain perception of autonomous vehicles. However, previous works have shown that the general adversarial training-based methods can lead to indistinguishable features, resulting in a decline in the robustness of perception. In this regard, we adopted contrastive learning to guarantee the proximity of similar samples, and the principle of different classes of samples to a certain extent. This ensures the closeness of similar samples and upholds the feature distinction between different classes of samples to a significant degree. Thus, we proposed a novel domain adversarial training framework incorporating the contrastive learning method to enhance cross-domain feature recognition for autonomous driving systems. We empirically evaluate the proposed method against several recent baselines showing improved benchmark performances, confirming the effectiveness of the proposed method.

Linux as a GPOS has the advantages of high average system throughput performance, a large number of open-source solutions, etc. It is a mature and complete operating system that can be used for in-vehicle system development. However, the vehicle in motion will produce a large number of real-time tasks, that need to be processed by the system promptly, and Linux's kernel preemption mechanism and interrupt mechanism are not designed to deal with real-time tasks, so they need to be improved. In this paper, we analyze the operation principle of each part of the Linux system, expound on the shortcomings of Linux as a real-time system, and then analyze the enhancement principle of Preempt_RT and Xenomai two kinds of patches on Linux real-time, and finally, we analyze the experimental data by carrying out experiments and applying probabilistic statistics to derive the results of Xenomai and Preempt_RT for Xenomai and Preempt_RT improve the task response latency of Linux system by 250% and 114%, respectively.

Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. In this work, we propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning. By modeling the parameter transitions along the sequential tasks with the weight matrix transformation, we propose to apply the low-rank approximation on the task-adaptive parameters in each layer of the neural networks. Specifically, we theoretically demonstrate the quantitative relationship between the Hessian and the proposed low-rank approximation. The approximation ranks are then globally determined according to the marginal change of the empirical loss estimated by the layer-specific gradient and low-rank approximation error. Furthermore, we control the model capacity by pruning less important parameters to diminish the parameter growth. We conduct extensive experiments on various benchmarks, including a dataset with large-scale tasks, and compare our method against some recent state-of-the-art methods to demonstrate the effectiveness and scalability of our proposed method. Empirical results show that our method performs better on different benchmarks, especially in achieving task order robustness and handling the forgetting issue.

Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a self-driving car with a vision system drives from dawn to dusk, with the sky gradually darkening. Therefore, the system must be able to adapt to changes in ambient illuminations and continue to drive safely on the road. In this paper, we formulate such problems as Evolving Domain Generalization, where a model aims to generalize well on a target domain by discovering and leveraging the evolving pattern of the environment. We then propose Directional Domain Augmentation (DDA), which simulates the unseen target features by mapping source data as augmentations through a domain transformer. Specifically, we formulate DDA as a bi-level optimization problem and solve it through a novel meta-learning approach in the representation space. We evaluate the proposed method on both synthetic datasets and real-world datasets, and empirical results show that our approach can outperform other existing methods.

Learning from multiple related tasks by knowledge sharing and transfer has become increasingly relevant over the last two decades. In order to successfully transfer information from one task to another, it is critical to understand the similarities and differences between the domains. In this paper, we introduce the notion of performance gap, an intuitive and novel measure of the distance between learning tasks. Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e.g., $\mathcal{H}$-divergence or discrepancy distance), we theoretically show that the performance gap can be viewed as a data- and algorithm-dependent regularizer, which controls the model complexity and leads to finer guarantees. More importantly, it also provides new insights and motivates a novel principle for designing strategies for knowledge sharing and transfer: gap minimization. We instantiate this principle with two algorithms: 1. gapBoost, a novel and principled boosting algorithm that explicitly minimizes the performance gap between source and target domains for transfer learning; and 2. gapMTNN, a representation learning algorithm that reformulates gap minimization as semantic conditional matching for multitask learning. Our extensive evaluation on both transfer learning and multitask learning benchmark data sets shows that our methods outperform existing baselines.

In this article, we present an analysis of unsupervised domain adaptation with a series of theoretical and algorithmic results. We derive a novel Rényi-$\alpha$divergence-based generalization bound, which is tailored to domain adaptation algorithms with arbitrary loss functions in a stochastic setting. Moreover, our theoretical results provide new insights into the assumptions for successful domain adaptation: the closeness between the conditional distributions of the domains and the Lipschitzness on the source domain. With these assumptions, we reveal the following: if their conditional generation distributions are close, the Lipschitzness property of the target domain can be transferred from the Lipschitzness on the source domain, without knowing the exact target distribution. Motivated by our analysis and assumptions, we further derive practical principles for deep domain adaptation: 1) Rényi-2 adversarial training for marginal distributions matching and 2) Lipschitz regularization for the classifier. Our experimental results on both synthetic and real-world datasets support our theoretical findings and the practical efficiency of the proposed principles.

In this paper, we study two dimensional metric learning (2DML) for matrix data from both theoretical and algorithmic perspectives. We first investigate the generalization bounds of 2DML based on the notion of Rademacher complexity, which theoretically justifies the benefits of learning from matrices directly. Furthermore, we present a novel boosting-based algorithm that scales well with the feature dimension. Finally, we introduce an efficient rank-one correction algorithm, which is tailored to our boosting learning procedure to produce a low-rank solution to 2DML. As our algorithm works directly on the data in matrix representation, it scales well with the feature dimension, keeps the structure and dependence in the data, and has a more compact structure and much fewer parameters to optimize. Extensive evaluations on several benchmark data sets also empirically verify the effectiveness and efficiency of our algorithm.

One crucial objective of multi-task learning is to align distributions across tasks so that the information between them can be transferred and shared. However, existing approaches only focused on matching the marginal feature distribution while ignoring the semantic information, which may hinder the learning performance. To address this issue, we propose to leverage the label information in multi-task learning by exploring the semantic conditional relations among tasks. We first theoretically analyze the generalization bound of multi-task learning based on the notion of Jensen-Shannon divergence, which provides new insights into the value of label information in multi-task learning. Our analysis also leads to a concrete algorithm that jointly matches the semantic distribution and controls label distribution divergence. To confirm the effectiveness of the proposed method, we first compare the algorithm with several baselines on some benchmarks and then test the algorithms under label space shift conditions. Empirical results demonstrate that the proposed method could outperform most baselines and achieve state-of-the-art performance, particularly showing the benefits under the label shift conditions.

Multitask learning (MTL) aims at solving the related tasks simultaneously by exploiting shared knowledge to improve performance on individual tasks. Though numerous empirical results supported the notion that such shared knowledge among tasks plays an essential role in MTL, the theoretical understanding of the relationships between tasks and their impact on learning shared knowledge is still an open problem. In this work, we are developing a theoretical perspective of the benefits involved in using information similarity for MTL. To this end, we first propose an upper bound on the generalization error by implementing the Wasserstein distance as the similarity metric. This indicates the practical principles of applying the similarity information to control the generalization errors. Based on those theoretical results, we revisited the adversarial multitask neural network and proposed a new training algorithm to learn the task relation coefficients and neural network parameters automatically. The computer vision benchmarks reveal the abilities of the proposed algorithms to improve the empirical performance. Finally, we test the proposed approach on real medical data sets, showing its advantage for extracting task relations.

In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning. We are providing theoretical insights from the intuition of modeling the interactive procedure in active learning as distribution matching, by adopting the Wasserstein distance. As a consequence, we derived a new training loss from the theoretical analysis, which is decomposed into optimizing deep neural network parameters and batch query selection through alternative optimization. In addition, the loss for training a deep neural network is naturally formulated as a min-max optimization problem through leveraging the unlabeled data information. Moreover, the proposed principles also indicate an explicit uncertainty-diversity trade-off in the query batch selection. Finally, we evaluate our proposed method on different benchmarks, consistently showing better empirical performances and a better time-efficient query strategy compared to the baselines.