arXiv subjects

Zixin Wang

Publications and source records attributed to Zixin Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

EnergyPatchTST: Multi-scale Time Series Transformers with Uncertainty Estimation for Energy Forecasting

Accurate and reliable energy time series prediction is of great significance for power generation planning and allocation. At present, deep learning time series prediction has become the mainstream method. However, the multi-scale time dynamics and the irregularity of real data lead to the limitations of the existing methods. Therefore, we propose EnergyPatchTST, which is an extension of the Patch Time Series Transformer specially designed for energy forecasting. The main innovations of our method are as follows: (1) multi-scale feature extraction mechanism to capture patterns with different time resolutions; (2) probability prediction framework to estimate uncertainty through Monte Carlo elimination; (3) integration path of future known variables (such as temperature and wind conditions); And (4) Pre-training and Fine-tuning examples to enhance the performance of limited energy data sets. A series of experiments on common energy data sets show that EnergyPatchTST is superior to other commonly used methods, the prediction error is reduced by 7-12%, and reliable uncertainty estimation is provided, which provides an important reference for time series prediction in the energy field.

cs.LG↗

arXiv2025

Edge Large AI Models: Collaborative Deployment and IoT Applications

Large artificial intelligence models (LAMs) emulate human-like problem-solving capabilities across diverse domains, modalities, and tasks. By leveraging the communication and computation resources of geographically distributed edge devices, edge LAMs enable real-time intelligent services at the network edge. Unlike conventional edge AI, which relies on small or moderate-sized models for direct feature-to-prediction mappings, edge LAMs leverage the intricate coordination of modular components to enable context-aware generative tasks and multi-modal inference. We shall propose a collaborative deployment framework for edge LAM by characterizing the LAM intelligent capabilities and limited edge network resources. Specifically, we propose a collaborative training framework over heterogeneous edge networks that adaptively decomposes LAMs according to computation resources, data modalities, and training objectives, reducing communication and computation overheads during the fine-tuning process. Furthermore, we introduce a microservice-based inference framework that virtualizes the functional modules of edge LAMs according to their architectural characteristics, thereby improving resource utilization and reducing inference latency. The developed edge LAM will provide actionable solutions to enable diversified Internet-of-Things (IoT) applications, facilitated by constructing mappings from diverse sensor data to token representations and fine-tuning based on domain knowledge.

cs.IT↗

arXiv2025

Edge Large AI Models: Revolutionizing 6G Networks

Large artificial intelligence models (LAMs) possess human-like abilities to solve a wide range of real-world problems, exemplifying the potential of experts in various domains and modalities. By leveraging the communication and computation capabilities of geographically dispersed edge devices, edge LAM emerges as an enabling technology to empower the delivery of various real-time intelligent services in 6G. Unlike traditional edge artificial intelligence (AI) that primarily supports a single task using small models, edge LAM is featured by the need of the decomposition and distributed deployment of large models, and the ability to support highly generalized and diverse tasks. However, due to limited communication, computation, and storage resources over wireless networks, the vast number of trainable neurons and the substantial communication overhead pose a formidable hurdle to the practical deployment of edge LAMs. In this paper, we investigate the opportunities and challenges of edge LAMs from the perspectives of model decomposition and resource management. Specifically, we propose collaborative fine-tuning and full-parameter training frameworks, alongside a microservice-assisted inference architecture, to enhance the deployment of edge LAM over wireless networks. Additionally, we investigate the application of edge LAM in air-interface designs, focusing on channel prediction and beamforming. These innovative frameworks and applications offer valuable insights and solutions for advancing 6G technology.

cs.NI↗

arXiv2025

Mutual Information-Empowered Task-Oriented Communication: Principles, Applications and Challenges

Mutual information (MI)-based guidelines have recently proven to be effective for designing task-oriented communication systems, where the ultimate goal is to extract and transmit task-relevant information for downstream task. This paper provides a comprehensive overview of MI-empowered task-oriented communication, highlighting how MI-based methods can serve as a unifying design framework in various task-oriented communication scenarios. We begin with the roadmap of MI for designing task-oriented communication systems, and then introduce the roles and applications of MI to guide feature encoding, transmission optimization, and efficient training with two case studies. We further elaborate the limitations and challenges of MI-based methods. Finally, we identify several open issues in MI-based task-oriented communication to inspire future research.

cs.IT↗

arXiv2025

Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation

Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Test-time adaptation (TTA) mitigates this issue by adjusting components like normalization layers or context prompts, yet it typically requires large batch sizes and extensive augmentations, leading to high computational costs. This raises a key question: Can VLMs' performance drop in specific test cases be mitigated through efficient, training-free approaches? To explore the solution, we investigate token condensation (TC) techniques, originally designed to enhance vision transformer efficiency by refining token usage during inference. We observe that informative tokens improve visual-text alignment in VLMs like CLIP on unseen datasets. However, existing TC methods often fail to maintain in-distribution performance when reducing tokens, prompting us to ask: How can we transform TC into an effective ``free-lunch'' adaptation strategy for VLMs? To address this, we propose Token Condensation as Adaptation (TCA), a training-free adaptation method that takes a step beyond standard TC. Rather than passively discarding tokens, TCA condenses token representation by introducing reservoir-based domain anchor tokens for information-preserving token reduction and logits correction. TCA achieves up to a 21.4% performance improvement over the strongest baseline on cross-dataset benchmark and the CIFAR-100-Corrupted dataset while reducing GFLOPs by 12.2% to 48.9%, with minimal hyperparameter dependency on both CLIP and SigLIP series.

cs.CV↗

arXiv2024

Federated Low-Rank Adaptation with Differential Privacy over Wireless Networks

Fine-tuning large pre-trained foundation models (FMs) on distributed edge devices presents considerable computational and privacy challenges. Federated fine-tuning (FedFT) mitigates some privacy issues by facilitating collaborative model training without the need to share raw data. To lessen the computational burden on resource-limited devices, combining low-rank adaptation (LoRA) with federated learning enables parameter-efficient fine-tuning. Additionally, the split FedFT architecture partitions an FM between edge devices and a central server, reducing the necessity for complete model deployment on individual devices. However, the risk of privacy eavesdropping attacks in FedFT remains a concern, particularly in sensitive areas such as healthcare and finance. In this paper, we propose a split FedFT framework with differential privacy (DP) over wireless networks, where the inherent wireless channel noise in the uplink transmission is utilized to achieve DP guarantees without adding an extra artificial noise. We shall investigate the impact of the wireless noise on convergence performance of the proposed framework. We will also show that by updating only one of the low-rank matrices in the split FedFT with DP, the proposed method can mitigate the noise amplification effect. Simulation results will demonstrate that the proposed framework achieves higher accuracy under strict privacy budgets compared to baseline methods.

cs.LG↗

arXiv2024

Open-CRB: Towards Open World Active Learning for 3D Object Detection

LiDAR-based 3D object detection has recently seen significant advancements through active learning (AL), attaining satisfactory performance by training on a small fraction of strategically selected point clouds. However, in real-world deployments where streaming point clouds may include unknown or novel objects, the ability of current AL methods to capture such objects remains unexplored. This paper investigates a more practical and challenging research task: Open World Active Learning for 3D Object Detection (OWAL-3D), aimed at acquiring informative point clouds with new concepts. To tackle this challenge, we propose a simple yet effective strategy called Open Label Conciseness (OLC), which mines novel 3D objects with minimal annotation costs. Our empirical results show that OLC successfully adapts the 3D detection model to the open world scenario with just a single round of selection. Any generic AL policy can then be integrated with the proposed OLC to efficiently address the OWAL-3D problem. Based on this, we introduce the Open-CRB framework, which seamlessly integrates OLC with our preliminary AL method, CRB, designed specifically for 3D object detection. We develop a comprehensive codebase for easy reproducing and future research, supporting 15 baseline methods (\textit{i.e.}, active learning, out-of-distribution detection and open world detection), 2 types of modern 3D detectors (\textit{i.e.}, one-stage SECOND and two-stage PV-RCNN) and 3 benchmark 3D datasets (\textit{i.e.}, KITTI, nuScenes and Waymo). Extensive experiments evidence that the proposed Open-CRB demonstrates superiority and flexibility in recognizing both novel and known classes with very limited labeling costs, compared to state-of-the-art baselines. Source code is available at \url{https://github.com/Luoyadan/CRB-active-3Ddet/tree/Open-CRB}.

cs.CV↗

arXiv2024

Research on Improved U-net Based Remote Sensing Image Segmentation Algorithm

In recent years, although U-Net network has made significant progress in the field of image segmentation, it still faces performance bottlenecks in remote sensing image segmentation. In this paper, we innovatively propose to introduce SimAM and CBAM attention mechanism in U-Net, and the experimental results show that after adding SimAM and CBAM modules alone, the model improves 17.41% and 12.23% in MIoU, and the Mpa and Accuracy are also significantly improved. And after fusing the two,the model performance jumps up to 19.11% in MIoU, and the Mpa and Accuracy are also improved by 16.38% and 14.8% respectively, showing excellent segmentation accuracy and visual effect with strong generalization ability and robustness. This study opens up a new path for remote sensing image segmentation technology and has important reference value for algorithm selection and improvement.

cs.DC↗

arXiv2024

Blockchain-Enabled Dynamic Spectrum Sharing for Satellite and Terrestrial Communication Networks

Dynamic spectrum sharing (DSS) between satellite and terrestrial networks has increasingly engaged the academic and industrial sectors. Nevertheless, facilitating secure, efficient and scalable sharing continues to pose a pivotal challenge. Emerging as a promising technology to bridge the trust gap among multiple participants, blockchain has been envisioned to enable DSS in a decentralized manner. However, satellites with limited resources may struggle to support the frequent interactions required by blockchain networks. Additionally,given the extensive coverage of satellites, spectrum sharing needs vary by regions, challenging traditional blockchain approaches to accommodate differences. In this work, a partitioned, self-governed, and customized dynamic spectrum sharing approach (PSC-DSS) is proposed for spectrum sharing between satellite access networks and terrestrial access networks. This approach establishes a sharded and tiered architecture which allows various regions to manage spectrum autonomously while jointly maintaining a single blockchain ledger. Moreover, a spectrum-consensus integrated mechanism, which decouples DSS process and couples it with blockchain consensus protocol, is designed to enable regions to conduct DSS transactions in parallel and dynamically innovate spectrum sharing schemes without affecting others. Furthermore, a theoretical framework is derived to justify the stability performance of PSC-DSS. Finally, simulations and experiments are conducted to validate the advantageous performance of PSC-DSS in terms of low-overhead, high efficiency, and robust stability.

cs.DC↗

arXiv2024

DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation

Semiparametric statistics play a pivotal role in a wide range of domains, including but not limited to missing data, causal inference, and transfer learning, to name a few. In many settings, semiparametric theory leads to (nearly) statistically optimal procedures that yet involve numerically solving Fredholm integral equations of the second kind. Traditional numerical methods, such as polynomial or spline approximations, are difficult to scale to multi-dimensional problems. Alternatively, statisticians may choose to approximate the original integral equations by ones with closed-form solutions, resulting in computationally more efficient, but statistically suboptimal or even incorrect procedures. To bridge this gap, we propose a novel framework by formulating the semiparametric estimation problem as a bi-level optimization problem; and then we develop a scalable algorithm called Deep Neural-Nets Assisted Semiparametric Estimation (DNA-SE) by leveraging the universal approximation property of Deep Neural-Nets (DNN) to streamline semiparametric procedures. Through extensive numerical experiments and a real data analysis, we demonstrate the numerical and statistical advantages of $\dnase$ over traditional methods. To the best of our knowledge, we are the first to bring DNN into semiparametric statistics as a numerical solver of integral equations in our proposed general framework.

stat.ML↗

arXiv2024

DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection

LiDAR-based 3D object detection has seen impressive advances in recent times. However, deploying trained 3D detectors in the real world often yields unsatisfactory performance when the distribution of the test data significantly deviates from the training data due to different weather conditions, object sizes, \textit{etc}. A key factor in this performance degradation is the diminished generalizability of pre-trained models, which creates a sharp loss landscape during training. Such sharpness, when encountered during testing, can precipitate significant performance declines, even with minor data variations. To address the aforementioned challenges, we propose \textbf{dual-perturbation optimization (DPO)} for \textbf{\underline{T}est-\underline{t}ime \underline{A}daptation in \underline{3}D \underline{O}bject \underline{D}etection (TTA-3OD)}. We minimize the sharpness to cultivate a flat loss landscape to ensure model resiliency to minor data variations, thereby enhancing the generalization of the adaptation process. To fully capture the inherent variability of the test point clouds, we further introduce adversarial perturbation to the input BEV features to better simulate the noisy test environment. As the dual perturbation strategy relies on trustworthy supervision signals, we utilize a reliable Hungarian matcher to filter out pseudo-labels sensitive to perturbations. Additionally, we introduce early Hungarian cutoff to avoid error accumulation from incorrect pseudo-labels by halting the adaptation process. Extensive experiments across three types of transfer tasks demonstrate that the proposed DPO significantly surpasses previous state-of-the-art approaches, specifically on Waymo $\rightarrow$ KITTI, outperforming the most competitive baseline by 57.72\% in $\text{AP}_\text{3D}$ and reaching 91\% of the fully supervised upper bound.

cs.CV↗

arXiv2024

In Search of Lost Online Test-time Adaptation: A Survey

This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing on effectively adapting machine learning models to distributionally different target data upon batch arrival. Despite the recent proliferation of OTTA methods, conclusions from previous studies are inconsistent due to ambiguous settings, outdated backbones, and inconsistent hyperparameter tuning, which obscure core challenges and hinder reproducibility. To enhance clarity and enable rigorous comparison, we classify OTTA techniques into three primary categories and benchmark them using a modern backbone, the Vision Transformer (ViT). Our benchmarks cover conventional corrupted datasets such as CIFAR-10/100-C and ImageNet-C, as well as real-world shifts represented by CIFAR-10.1, OfficeHome, and CIFAR-10-Warehouse. The CIFAR-10-Warehouse dataset includes a variety of variations from different search engines and synthesized data generated through diffusion models. To measure efficiency in online scenarios, we introduce novel evaluation metrics, including GFLOPs, wall clock time, and GPU memory usage, providing a clearer picture of the trade-offs between adaptation accuracy and computational overhead. Our findings diverge from existing literature, revealing that (1) transformers demonstrate heightened resilience to diverse domain shifts, (2) the efficacy of many OTTA methods relies on large batch sizes, and (3) stability in optimization and resistance to perturbations are crucial during adaptation, particularly when the batch size is 1. Based on these insights, we highlight promising directions for future research. Our benchmarking toolkit and source code are available at https://github.com/Jo-wang/OTTA_ViT_survey.

cs.AI↗

arXiv2024

Federated Fine-Tuning for Pre-Trained Foundation Models Over Wireless Networks

Pre-trained foundation models (FMs), with extensive number of neurons, are key to advancing next-generation intelligence services, where personalizing these models requires massive amount of task-specific data and computational resources. The prevalent solution involves centralized processing at the edge server, which, however, raises privacy concerns due to the transmission of raw data. Instead, federated fine-tuning (FedFT) is an emerging privacy-preserving fine-tuning (FT) paradigm for personalized pre-trained foundation models. In particular, by integrating low-rank adaptation (LoRA) with federated learning (FL), federated LoRA enables the collaborative FT of a global model with edge devices, achieving comparable learning performance to full FT while training fewer parameters over distributed data and preserving raw data privacy. However, the limited radio resources and computation capabilities of edge devices pose significant challenges for deploying federated LoRA over wireless networks. To this paper, we propose a split federated LoRA framework, which deploys the computationally-intensive encoder of a pre-trained model at the edge server, while keeping the embedding and task modules at the edge devices. Building on this split framework, the paper provides a rigorous analysis of the upper bound of the convergence gap for the wireless federated LoRA system. This analysis motivates the formulation of a long-term upper bound minimization problem, where we decompose the formulated long-term mixed-integer programming (MIP) problem into sequential sub-problems using the Lyapunov technique. We then develop an online algorithm for effective device scheduling and bandwidth allocation. Simulation results demonstrate the effectiveness of the proposed online algorithm in enhancing learning performance.

eess.SY↗

arXiv2024

Machine Unlearning in Contrastive Learning

Machine unlearning is a complex process that necessitates the model to diminish the influence of the training data while keeping the loss of accuracy to a minimum. Despite the numerous studies on machine unlearning in recent years, the majority of them have primarily focused on supervised learning models, leaving research on contrastive learning models relatively underexplored. With the conviction that self-supervised learning harbors a promising potential, surpassing or rivaling that of supervised learning, we set out to investigate methods for machine unlearning centered around contrastive learning models. In this study, we introduce a novel gradient constraint-based approach for training the model to effectively achieve machine unlearning. Our method only necessitates a minimal number of training epochs and the identification of the data slated for unlearning. Remarkably, our approach demonstrates proficient performance not only on contrastive learning models but also on supervised learning models, showcasing its versatility and adaptability in various learning paradigms.

cs.LG↗

arXiv2024

Membership Information Leakage in Federated Contrastive Learning

Federated Contrastive Learning (FCL) represents a burgeoning approach for learning from decentralized unlabeled data while upholding data privacy. In FCL, participant clients collaborate in learning a global encoder using unlabeled data, which can serve as a versatile feature extractor for diverse downstream tasks. Nonetheless, FCL is susceptible to privacy risks, such as membership information leakage, stemming from its distributed nature, an aspect often overlooked in current solutions. This study delves into the feasibility of executing a membership inference attack on FCL and proposes a robust attack methodology. The attacker's objective is to determine if the data signifies training member data by accessing the model's inference output. Specifically, we concentrate on attackers situated within a client framework, lacking the capability to manipulate server-side aggregation methods or discern the training status of other clients. We introduce two membership inference attacks tailored for FCL: the \textit{passive membership inference attack} and the \textit{active membership inference attack}, contingent on the attacker's involvement in local model training. Experimental findings across diverse datasets validate the effectiveness of our attacks and underscore the inherent privacy risks associated with the federated contrastive learning paradigm.

cs.CR↗

arXiv2024

Machine Unlearning in Large Language Models

Recently, large language models (LLMs) have emerged as a notable field, attracting significant attention for its ability to automatically generate intelligent contents for various application domains. However, LLMs still suffer from significant security and privacy issues. For example, LLMs might expose user privacy from hacking attacks or targeted prompts. To address this problem, this paper introduces a novel machine unlearning framework into LLMs. Our objectives are to make LLMs not produce harmful, hallucinatory, or privacy-compromising responses, while retaining their standard output capabilities. To accomplish this, we use an evaluative model to pinpoint dialogues needing unlearning. We also establish a distance loss to function as the model's negative loss, diverting it from previous undesirable outputs. Furthermore, we determine the expected output's cluster mean to formulate a positive loss, directing the model's outputs toward preferable outcomes without compromising its reasoning abilities and performance. Experimental results show that our approach effectively meets unlearning objectives without substantially compromising model performance.

cs.CR↗

arXiv2023

Energy Demand Unawareness and the Popularity of Bitcoin: Evidence from Nigeria

Decentralized cryptocurrency networks, notably those with high energy demand, have faced significant criticism and subsequent regulatory scrutiny. Despite these concerns, policy interventions targeting cryptocurrency operations in the pursuit of sustainability have largely been ineffective. Some were abandoned for fear of jeopardizing innovation, whereas others failed due to the highly globalized nature of blockchain systems. In search of a more effective angle for energy policy measures, this study adopts a consumer-centric perspective, examining the sentiments of Nigerian cryptocurrency users (${n=158}$) toward Bitcoin's sustainability, a representative cryptocurrency known for its high electricity demand. Three main findings emerged: 1) Even among those self-identifying as highly knowledgeable, most considerably underestimated Bitcoin's electricity consumption. 2) Participants with a more accurate understanding of Bitcoin's energy demand were more inclined to support sustainability measures. 3) Most of this supportive cohort viewed private entities as the primary stakeholders for implementing such measures. Given these findings, we suggest that consumer education should be at the forefront of policy initiatives aimed at cryptocurrency sustainability.

cs.CY↗

arXiv2023

Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error

The prevalence of domain adaptive semantic segmentation has prompted concerns regarding source domain data leakage, where private information from the source domain could inadvertently be exposed in the target domain. To circumvent the requirement for source data, source-free domain adaptation has emerged as a viable solution that leverages self-training methods to pseudo-label high-confidence regions and adapt the model to the target data. However, the confidence scores obtained are often highly biased due to over-confidence and class-imbalance issues, which render both model selection and optimization problematic. In this paper, we propose a novel calibration-guided source-free domain adaptive semantic segmentation (Cal-SFDA) framework. The core idea is to estimate the expected calibration error (ECE) from the segmentation predictions, serving as a strong indicator of the model's generalization capability to the unlabeled target domain. The estimated ECE scores, in turn, assist the model training and fair selection in both source training and target adaptation stages. During model pre-training on the source domain, we ensure the differentiability of the ECE objective by leveraging the LogSumExp trick and using ECE scores to select the best source checkpoints for adaptation. To enable ECE estimation on the target domain without requiring labels, we train a value net for ECE estimation and apply statistic warm-up on its BatchNorm layers for stability. The estimated ECE scores assist in determining the reliability of prediction and enable class-balanced pseudo-labeling by positively guiding the adaptation progress and inhibiting potential error accumulation. Extensive experiments on two widely-used synthetic-to-real transfer tasks show that the proposed approach surpasses previous state-of-the-art by up to 5.25% of mIoU with fair model selection criteria.

cs.CV↗