Xiaozhou Ye

Yang Liu, Yan Kang, Tianyuan Zou et al.

Vertical Federated Learning (VFL) is a federated learning setting where multiple parties with different features about the same set of users jointly train machine learning models without exposing their raw data or model parameters. Motivated by the rapid growth in VFL research and real-world applications, we provide a comprehensive review of the concept and algorithms of VFL, as well as current advances and challenges in various aspects, including effectiveness, efficiency, and privacy. We provide an exhaustive categorization for VFL settings and privacy-preserving protocols and comprehensively analyze the privacy attacks and defense strategies for each protocol. In the end, we propose a unified framework, termed VFLow, which considers the VFL problem under communication, computation, privacy, as well as effectiveness and fairness constraints. Finally, we review the most recent advances in industrial applications, highlighting open challenges and future directions for VFL.

Rui Kong, Yuanchun Li, Qingtian Feng et al.

Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts. However, serving MoE models on memory-constrained devices is challenging due to the large parameter size. Typical solutions such as memory swapping or expert pruning may lead to significantly higher latency or severe accuracy loss. In this paper, we introduce SwapMoE, a framework for efficient serving of MoE-based large language models with tunable memory budgets. The main idea of SwapMoE is to keep a small dynamic set of important experts, namely Virtual Experts, in the main memory for inference, while seamlessly maintaining how the Virtual Experts map to the actual experts. Experiments have shown that SwapMoE can reduce the memory footprint while maintaining reasonable accuracy. For example, on text summarization tasks with Switch Transformer, SwapMoE can reduce the memory consumption from 14.2 GiB to 4.7 GiB, together with 50\% latency reduction and a slight Rouge-2 score drop of 0.041.

Hao Wen, Yuanchun Li, Zunshuai Zhang et al.

Deep learning models are increasingly deployed to edge devices for real-time applications. To ensure stable service quality across diverse edge environments, it is highly desirable to generate tailored model architectures for different conditions. However, conventional pre-deployment model generation approaches are not satisfactory due to the difficulty of handling the diversity of edge environments and the demand for edge information. In this paper, we propose to adapt the model architecture after deployment in the target environment, where the model quality can be precisely measured and private edge data can be retained. To achieve efficient and effective edge model generation, we introduce a pretraining-assisted on-cloud model elastification method and an edge-friendly on-device architecture search method. Model elastification generates a high-quality search space of model architectures with the guidance of a developer-specified oracle model. Each subnet in the space is a valid model with different environment affinity, and each device efficiently finds and maintains the most suitable subnet based on a series of edge-tailored optimizations. Extensive experiments on various edge devices demonstrate that our approach is able to achieve significantly better accuracy-latency tradeoffs (e.g. 46.74\% higher on average accuracy with a 60\% latency budget) than strong baselines with minimal overhead (13 GPU hours in the cloud and 2 minutes on the edge server).

Tianyuan Zou, Yang Liu, Peng Li et al. · tsinghua

Substantial quantity and high quality are the golden rules of making a good training dataset with sample privacy protection equally important. Generating synthetic samples that resemble high-quality private data while ensuring Differential Privacy (DP), a formal privacy guarantee, promises scalability and practicality. However, existing methods relying on pre-trained models for data synthesis %that avoid fine-tuning large pre-trained generative models often struggle in data-deficient scenarios, suffering from limited sample size, inevitable generation noise and existing pre-trained model bias. To address these challenges, we propose a novel contrAstive private data Synthesis via Weighted multiple Pre-trained language models (PLM) framework, named as WASP. WASP utilizes limited private samples for more accurate private data distribution estimation via a Top-Q voting mechanism, and leverages low-quality synthetic samples for contrastive generation via collaboration among dynamically weighted multiple pre-trained models.Extensive experiments on 6 well-developed datasets with 6 open-source and 3 closed-source PLMs demonstrate the superiority of WASP in improving model performance over diverse downstream tasks. Code is available at https://anonymous.4open.science/r/WASP.

Aidong Yang, Mohan Wu, Boquan Cheng et al.

As computing power is becoming the core productivity of the digital economy era, the concept of Computing and Network Convergence (CNC), under which network and computing resources can be dynamically scheduled and allocated according to users' needs, has been proposed and attracted wide attention. Based on the tasks' properties, the network orchestration plane needs to flexibly deploy tasks to appropriate computing nodes and arrange paths to the computing nodes. This is a orchestration problem that involves resource scheduling and path arrangement. Since CNC is relatively new, in this paper, we review some researches and applications on CNC. Then, we design a CNC orchestration method using reinforcement learning (RL), which is the first attempt, that can flexibly allocate and schedule computing resources and network resources. Which aims at high profit and low latency. Meanwhile, we use multi-factors to determine the optimization objective so that the orchestration strategy is optimized in terms of total performance from different aspects, such as cost, profit, latency and system overload in our experiment. The experiments shows that the proposed RL-based method can achieve higher profit and lower latency than the greedy method, random selection and balanced-resource method. We demonstrate RL is suitable for CNC orchestration. This paper enlightens the RL application on CNC orchestration.

Jiacheng Yin, Wenwen Li, Xidong Wang et al.

With the development of 4G/5G, the rapid growth of traffic has caused a large number of cell indicators to exceed the warning threshold, and network quality has deteriorated. It is necessary for operators to solve the congestion in advance and effectively to guarantee the quality of user experience. Cell-level multi-indicator forecasting is the foundation task for proactive complex network optimization. In this paper, we propose the 4G/5G Cell-level multi-indicator forecasting method based on the dense-Multi-Layer Perceptron (MLP) neural network, which adds additional fully-connected layers between non-adjacent layers in an MLP network. The model forecasted the following week's traffic indicators of 13000 cells according to the six-month historical indicators of 65000 cells in the 4G&5G network, which got the highest weighted MAPE score (0.2484) in the China Mobile problem statement in the ITU-T AI/ML in 5G Challenge 2021. Furthermore, the proposed model has been integrated into the AsiaInfo 4G/5G energy-saving system and deployed in Jiangsu Province of China.

Ye Ouyang, Yaqin Zhang, Xiaozhou Ye et al.

In the global craze of GPT, people have deeply realized that AI, as a transformative technology and key force in economic and social development, will bring great leaps and breakthroughs to the global industry and profoundly influence the future world competition pattern. As the builder and operator of information and communication infrastructure, the telecom sector provides infrastructure support for the development of AI, and even takes the lead in the implementation of AI applications. How to enable the application of AIGC (GPT) and implement AIGC in the telecom sector are questions that telecom practitioners must ponder and answer. Through the study of GPT, a typical representative of AIGC, the authors have analyzed how GPT empowers the telecom sector in the form of scenarios, discussed the gap between the current GPT general model and telecom services, proposed for the first time a Telco Augmented Cognition capability system, provided answers to how to construct a telecom service GPT in the telecom sector, and carried out various practices. Our counterparts in the industry are expected to focus on collaborative innovation around telecom and AI, build an open and shared innovation ecosystem, promote the deep integration of AI and telecom sector, and accelerate the construction of next-generation information infrastructure, in an effort to facilitate the digital transformation of the economy and society.

Xiaozhou Ye, Feng Jiang, Zihan Wang et al.

Human Activity Recognition using wearable inertial sensors is foundational to healthcare monitoring, fitness analytics, and context-aware computing, yet its deployment is hindered by cross-user variability arising from heterogeneous physiological traits, motor habits, and sensor placements. Existing domain generalization approaches either neglect temporal dependencies in sensor streams or depend on impractical target-domain annotations. We propose a different paradigm: modeling generalizable feature extraction as a collaborative sequential generation process governed by reinforcement learning. Our framework, CTFG (Collaborative Temporal Feature Generation), employs a Transformer-based autoregressive generator that incrementally constructs feature token sequences, each conditioned on prior context and the encoded sensor input. The generator is optimized via Group-Relative Policy Optimization, a critic-free algorithm that evaluates each generated sequence against a cohort of alternatives sampled from the same input, deriving advantages through intra-group normalization rather than learned value estimation. This design eliminates the distribution-dependent bias inherent in critic-based methods and provides self-calibrating optimization signals that remain stable across heterogeneous user distributions. A tri-objective reward comprising class discrimination, cross-user invariance, and temporal fidelity jointly shapes the feature space to separate activities, align user distributions, and preserve fine-grained temporal content. Evaluations on the DSADS and PAMAP2 benchmarks demonstrate state-of-the-art cross-user accuracy (88.53\% and 75.22\%), substantial reduction in inter-task training variance, accelerated convergence, and robust generalization under varying action-space dimensionalities.

Xiaozhou Ye, Kevin I-Kai Wang

Human Activity Recognition (HAR) plays a crucial role in various applications such as human-computer interaction and healthcare monitoring. However, challenges persist in HAR models due to the data distribution differences between training and real-world data distributions, particularly evident in cross-user scenarios. This paper introduces a novel framework, termed Diffusion-based Noise-centered Adversarial Learning Domain Adaptation (Diff-Noise-Adv-DA), designed to address these challenges by leveraging generative diffusion modeling and adversarial learning techniques. Traditional HAR models often struggle with the diversity of user behaviors and sensor data distributions. Diff-Noise-Adv-DA innovatively integrates the inherent noise within diffusion models, harnessing its latent information to enhance domain adaptation. Specifically, the framework transforms noise into a critical carrier of activity and domain class information, facilitating robust classification across different user domains. Experimental evaluations demonstrate the effectiveness of Diff-Noise-Adv-DA in improving HAR model performance across different users, surpassing traditional domain adaptation methods. The framework not only mitigates distribution mismatches but also enhances data quality through noise-based denoising techniques.

Xiaozhou Ye, Kouichi Sakurai, Nirmal Nair et al.

Sensor-based Human Activity Recognition (HAR) is crucial in ubiquitous computing, analysing behaviours through multi-dimensional observations. Despite research progress, HAR confronts challenges, particularly in data distribution assumptions. Most studies often assume uniform data distributions across datasets, contrasting with the varied nature of practical sensor data in human activities. Addressing data heterogeneity issues can improve performance, reduce computational costs, and aid in developing personalized, adaptive models with less annotated data. This review investigates how machine learning addresses data heterogeneity in HAR, by categorizing data heterogeneity types, applying corresponding suitable machine learning methods, summarizing available datasets, and discussing future challenges.

Xiaozhou Ye, Kevin I-Kai Wang

In Human Activity Recognition (HAR), a predominant assumption is that the data utilized for training and evaluation purposes are drawn from the same distribution. It is also assumed that all data samples are independent and identically distributed ($\displaystyle i.i.d.$). Contrarily, practical implementations often challenge this notion, manifesting data distribution discrepancies, especially in scenarios such as cross-user HAR. Domain adaptation is the promising approach to address these challenges inherent in cross-user HAR tasks. However, a clear gap in domain adaptation techniques is the neglect of the temporal relation embedded within time series data during the phase of aligning data distributions. Addressing this oversight, our research presents the Deep Generative Domain Adaptation with Temporal Attention (DGDATA) method. This novel method uniquely recognises and integrates temporal relations during the domain adaptation process. By synergizing the capabilities of generative models with the Temporal Relation Attention mechanism, our method improves the classification performance in cross-user HAR. A comprehensive evaluation has been conducted on three public sensor-based HAR datasets targeting different scenarios and applications to demonstrate the efficacy of the proposed DGDATA method.

Xiaozhou Ye, Kevin I-Kai Wang

Current research on human activity recognition (HAR) mainly assumes that training and testing data are drawn from the same distribution to achieve a generalised model, which means all the data are considered to be independent and identically distributed $\displaystyle (i.i.d.) $. In many real-world applications, this assumption does not hold, and collected training and target testing datasets have non-uniform distribution, such as in the case of cross-user HAR. Domain adaptation is a promising approach for cross-user HAR tasks. Existing domain adaptation works based on the assumption that samples in each domain are $\displaystyle i.i.d. $ and do not consider the knowledge of temporal relation hidden in time series data for aligning data distribution. This strong assumption of $\displaystyle i.i.d. $ may not be suitable for time series-related domain adaptation methods because the samples formed by time series segmentation and feature extraction techniques are only coarse approximations to $\displaystyle i.i.d. $ assumption in each domain. In this paper, we propose the temporal relation optimal transport (TROT) method to utilise temporal relation and relax the $\displaystyle i.i.d. $ assumption for the samples in each domain for accurate and efficient knowledge transfer. We obtain the temporal relation representation and implement temporal relation alignment of activities via the Hidden Markov model (HMM) and optimal transport (OT) techniques. Besides, a new regularisation term that preserves temporal relation order information for an improved optimal transport mapping is proposed to enhance the domain adaptation performance. Comprehensive experiments are conducted on three public activity recognition datasets (i.e. OPPT, PAMAP2 and DSADS), demonstrating that TROT outperforms other state-of-the-art methods.

Xiaozhou Ye, Kevin I-Kai Wang

In human activity recognition (HAR), the assumption that training and testing data are independent and identically distributed (i.i.d.) often fails, particularly in cross-user scenarios where data distributions vary significantly. This discrepancy highlights the limitations of conventional domain adaptation methods in HAR, which typically overlook the inherent temporal relations in time-series data. To bridge this gap, our study introduces a Conditional Variational Autoencoder with Universal Sequence Mapping (CVAE-USM) approach, which addresses the unique challenges of time-series domain adaptation in HAR by relaxing the i.i.d. assumption and leveraging temporal relations to align data distributions effectively across different users. This method combines the strengths of Variational Autoencoder (VAE) and Universal Sequence Mapping (USM) to capture and utilize common temporal patterns between users for improved activity recognition. Our results, evaluated on two public HAR datasets (OPPT and PAMAP2), demonstrate that CVAE-USM outperforms existing state-of-the-art methods, offering a more accurate and generalizable solution for cross-user activity recognition.

Xiaozhou Ye, Waleed H. Abdulla, Nirmal Nair et al.

Human Activity Recognition (HAR) is a cornerstone of ubiquitous computing, with promising applications in diverse fields such as health monitoring and ambient assisted living. Despite significant advancements, sensor-based HAR methods often operate under the assumption that training and testing data have identical distributions. However, in many real-world scenarios, particularly in sensor-based HAR, this assumption is invalidated by out-of-distribution ($\displaystyle o.o.d.$) challenges, including differences from heterogeneous sensors, change over time, and individual behavioural variability. This paper centres on the latter, exploring the cross-user HAR problem where behavioural variability across individuals results in differing data distributions. To address this challenge, we introduce the Deep Temporal State Domain Adaptation (DTSDA) model, an innovative approach tailored for time series domain adaptation in cross-user HAR. Contrary to the common assumption of sample independence in existing domain adaptation approaches, DTSDA recognizes and harnesses the inherent temporal relations in the data. Therefore, we introduce 'Temporal State', a concept that defined the different sub-activities within an activity, consistent across different users. We ensure these sub-activities follow a logical time sequence through 'Temporal Consistency' property and propose the 'Pseudo Temporal State Labeling' method to identify the user-invariant temporal relations. Moreover, the design principle of DTSDA integrates adversarial learning for better domain adaptation. Comprehensive evaluations on three HAR datasets demonstrate DTSDA's superior performance in cross-user HAR applications by briding individual behavioral variability using temporal relations across sub-activities.

Yang Liu, Bingjie Yan, Tianyuan Zou et al.

Large language models (LLMs) have demonstrated remarkable capabilities, but they require vast amounts of data and computational resources. In contrast, smaller models (SMs), while less powerful, can be more efficient and tailored to specific domains. In this position paper, we argue that taking a collaborative approach, where large and small models work synergistically, can accelerate the adaptation of LLMs to private domains and unlock new potential in AI. We explore various strategies for model collaboration and identify potential challenges and opportunities. Building upon this, we advocate for industry-driven research that prioritizes multi-objective benchmarks on real-world private datasets and applications.

Chengtao Jian, Kai Yang, Ye Ouyang et al.

Direct Preference Optimization (DPO) has emerged as a popular and efficient alternative to reward modeling and reinforcement learning for aligning language models with human preferences. Despite its empirical success, the theoretical properties and intrinsic limitations of DPO remain underexplored. In this work, we first present a comprehensive analysis of DPO's dynamics from a probability evolution perspective. Our analysis reveals that DPO is highly sensitive to initialization. It also tends to misallocate probability mass, which can inadvertently shift probability toward irrelevant or undesired responses. This misallocation may unintentionally reinforce model bias, thereby compromising both the stability of model alignment and the consistency with intended preferences. Motivated by these theoretical findings, we propose a theoretically grounded bilevel optimization framework that tightly integrate supervised fine-tuning with an enhanced DPO objective a.k.a. stable preference optimization. Our approach introduces a principled regularization scheme to explicitly encourage absolute probability improvement for preferred outputs, while maintaining stable optimization dynamics. Experiments on challenging reasoning and summarization benchmarks elucidate that our method consistently improves reasoning accuracy and better aligns output distributions with intended preferences, outperforming standard DPO. Stable preference optimization provides new insights into the design of preference-based alignment objectives and opens up new avenues towards more reliable and interpretable language model alignment.

Ningxin He, Yang Liu, Wei Sun et al.

Text-to-Image (T2I) models have demonstrated their versatility in a wide range of applications. However, adaptation of T2I models to specialized tasks is often limited by the availability of task-specific data due to privacy concerns. On the other hand, harnessing the power of rich multimodal data from modern mobile systems and IoT infrastructures presents a great opportunity. This paper introduces Federated Multi-modal Knowledge Transfer (FedMMKT), a novel framework that enables co-enhancement of a server T2I model and client task-specific models using decentralized multimodal data without compromising data privacy.

Xiaozhou Ye, Kevin I-Kai Wang

Human Activity Recognition (HAR) using wearable sensors is crucial for healthcare, fitness tracking, and smart environments, yet cross-user variability -- stemming from diverse motion patterns, sensor placements, and physiological traits -- hampers generalization in real-world settings. Conventional supervised learning methods often overfit to user-specific patterns, leading to poor performance on unseen users. Existing domain generalization approaches, while promising, frequently overlook temporal dependencies or depend on impractical domain-specific labels. We propose Temporal-Preserving Reinforcement Learning Domain Generalization (TPRL-DG), a novel framework that redefines feature extraction as a sequential decision-making process driven by reinforcement learning. TPRL-DG leverages a Transformer-based autoregressive generator to produce temporal tokens that capture user-invariant activity dynamics, optimized via a multi-objective reward function balancing class discrimination and cross-user invariance. Key innovations include: (1) an RL-driven approach for domain generalization, (2) autoregressive tokenization to preserve temporal coherence, and (3) a label-free reward design eliminating the need for target user annotations. Evaluations on the DSADS and PAMAP2 datasets show that TPRL-DG surpasses state-of-the-art methods in cross-user generalization, achieving superior accuracy without per-user calibration. By learning robust, user-invariant temporal patterns, TPRL-DG enables scalable HAR systems, facilitating advancements in personalized healthcare, adaptive fitness tracking, and context-aware environments.

Kai Yang, Zelin Zhu, Chengtao Jian et al.

Urban general intelligence (UGI) refers to the capacity of AI systems to autonomously perceive, reason, and act within dynamic and complex urban environments. In this paper, we introduce UrbanMind, a tool-enhanced retrieval-augmented generation (RAG) framework designed to facilitate UGI. Central to UrbanMind is a novel architecture based on Continual Retrieval-Augmented MoE-based LLM (C-RAG-LLM), which dynamically incorporates domain-specific knowledge and evolving urban data to support long-term adaptability. The architecture of C-RAG-LLM aligns naturally with a multilevel optimization framework, where different layers are treated as interdependent sub-problems. Each layer has distinct objectives and can be optimized either independently or jointly through a hierarchical learning process. The framework is highly flexible, supporting both end-to-end training and partial layer-wise optimization based on resource or deployment constraints. To remain adaptive under data drift, it is further integrated with an incremental corpus updating mechanism. Evaluations on real-world urban tasks of a variety of complexity verify the effectiveness of the proposed framework. This work presents a promising step toward the realization of general-purpose LLM agents in future urban environments.

Shanhui Zhao, Hao Wen, Wenjie Du et al.

Large language models (LLMs) have opened new opportunities for automated mobile app exploration, an important and challenging problem that used to suffer from the difficulty of generating meaningful UI interactions. However, existing LLM-based exploration approaches rely heavily on LLMs to generate actions in almost every step, leading to a huge cost of token fees and computational resources. We argue that such extensive usage of LLMs is neither necessary nor effective, since many actions during exploration do not require, or may even be biased by the abilities of LLMs. Further, based on the insight that a precise and compact knowledge plays the central role for effective exploration, we introduce LLM-Explorer, a new exploration agent designed for efficiency and affordability. LLM-Explorer uses LLMs primarily for maintaining the knowledge instead of generating actions, and knowledge is used to guide action generation in a LLM-less manner. Based on a comparison with 5 strong baselines on 20 typical apps, LLM-Explorer was able to achieve the fastest and highest coverage among all automated app explorers, with over 148x lower cost than the state-of-the-art LLM-based approach.

Xiaozhou Ye, Kevin I-Kai Wang

Cross-user variability in Human Activity Recognition (HAR) remains a critical challenge due to differences in sensor placement, body dynamics, and behavioral patterns. Traditional methods often fail to capture biomechanical invariants that persist across users, limiting their generalization capability. We propose an Edge-Enhanced Graph-Based Adversarial Domain Generalization (EEG-ADG) framework that integrates anatomical correlation knowledge into a unified graph neural network (GNN) architecture. By modeling three biomechanically motivated relationships together-Interconnected Units, Analogous Units, and Lateral Units-our method encodes domain-invariant features while addressing user-specific variability through Variational Edge Feature Extractor. A Gradient Reversal Layer (GRL) enforces adversarial domain generalization, ensuring robustness to unseen users. Extensive experiments on OPPORTUNITY and DSADS datasets demonstrate state-of-the-art performance. Our work bridges biomechanical principles with graph-based adversarial learning by integrating information fusion techniques. This fusion of information underpins our unified and generalized model for cross-user HAR.

Xiaozhou Ye, Kevin I-Kai Wang

Cross-user variability poses a significant challenge in sensor-based Human Activity Recognition (HAR) systems, as traditional models struggle to generalize across users due to differences in behavior, sensor placement, and data distribution. To address this, we propose GNN-ADG (Graph Neural Network with Adversarial Domain Generalization), a novel method that leverages both the strength from both the Graph Neural Networks (GNNs) and adversarial learning to achieve robust cross-user generalization. GNN-ADG models spatial relationships between sensors on different anatomical body parts, extracting three types of Anatomical Units: (1) Interconnected Units, capturing inter-relations between neighboring sensors; (2) Analogous Units, grouping sensors on symmetrical or functionally similar body parts; and (3) Lateral Units, connecting sensors based on their position to capture region-specific coordination. These units information are fused into an unified graph structure with a cyclic training strategy, dynamically integrating spatial, functional, and lateral correlations to facilitate a holistic, user-invariant representation. Information fusion mechanism of GNN-ADG occurs by iteratively cycling through edge topologies during training, allowing the model to refine its understanding of inter-sensor relationships across diverse perspectives. By representing the spatial configuration of sensors as an unified graph and incorporating adversarial learning, Information Fusion GNN-ADG effectively learns features that generalize well to unseen users without requiring target user data during training, making it practical for real-world applications.