Machine learning models are widely integrated into modern mobile apps to analyze user behaviors and deliver personalized services. Ensuring low-latency on-device model execution is critical for maintaining high-quality user experiences. While prior research has primarily focused on accelerating model inference with given input features, we identify an overlooked bottleneck in real-world on-device model execution pipelines: extracting input features from raw application logs. In this work, we explore a new direction of feature extraction optimization by analyzing and eliminating redundant extraction operations across different model features and consecutive model inferences. We then introduce AutoFeature, an automated feature extraction engine designed to accelerate on-device feature extraction process without compromising model inference accuracy. AutoFeature comprises three core designs: (1) graph abstraction to formulate the extraction workflows of different input features as one directed acyclic graph, (2) graph optimization to identify and fuse redundant operation nodes across different features within the graph; (3) efficient caching to minimize operations on overlapping raw data between consecutive model inferences. We implement a system prototype of AutoFeature and integrate it into five industrial mobile services spanning search, video and e-commerce domains. Online evaluations show that AutoFeature reduces end-to-end on-device model execution latency by 1.33 × -3.93 × during daytime and 1.43 × -4.53 × at night.

In modern mobile and edge applications, users and devices frequently encounter dynamic contexts, necessitating ondevice continual learning (CL) to ensure consistent performance of machine learning models. While existing research predominantly focused on developing lightweight CL frameworks, we identify that data scarcity is a more severe bottleneck for ondevice CL. In this work, we explore the potential of leveraging abundant cloud-side data to enrich scarce on-device data, and propose Delta, a private, efficient and effective data enrichment framework. Specifically, Delta introduces a directory dataset to decompose the data enrichment problem into device-side and cloud-side sub-problems without sharing raw sensitive data, mitigating privacy concerns and reducing communication overhead. Next, Delta designs a soft data matching strategy to effectively solve device-side sub-problem with sparse user data and an optimal data sampling scheme for cloud server to efficiently retrieve the most suitable dataset for enrichment. Further, Delta refines the data sampling scheme by jointly considering the impact of enriched data on both new and past contexts, mitigating the catastrophic forgetting issue from a new aspect. Finally, we enhance Delta’s applicability to more private and rare user contexts by integrating differential privacy and domain adaptation techniques. Comprehensive experiments across four typical edge computing tasks with varied data modalities demonstrate that Delta significantly enhances overall model accuracy by an average of 15.1%, 12.4%, 1.1% and 5.6% for visual, IMU, audio and textual tasks compared with few-shot CL. Additionally, Delta reduces communication costs by over 90% compared to federated CL, making it suitable for resource-constrained edge networks.

Considering limited on-device resources, current practices are attempting to deploy a system-level mixture-of-experts (MoE)-based foundation LLM on a mobile device to serve multiple apps and support mobile intelligence. However, mobile apps are hard to customize their services that require fine-tuning adapters associated with the LLM using private in-app data. The difficulty arises due to both the limited on-device resources and the restricted control that apps have over the foundation LLM. To address this issue, in this work, we propose LiteMoE, a novel proxy submodel tuning framework that supports mobile apps to efficiently fine-tune customized adapters on devices using proxy submodels. The key technique behind LiteMoE is a post-training submodel extraction method, whereby without additional retraining, we can identify and reserve critical experts, match and merge moderate experts, to extract a lightweight and effective proxy submodel from the foundation LLM for a specific app. To further enhance scalability and adaptability, LiteMoE incorporates adapter reuse and continuous tuning mechanisms to handle multi-task requirements and evolving user preferences. We implemented a prototype of LiteMoE and evaluated it over various MoE-based LLMs and mobile computing tasks. The results show that with LiteMoE, mobile apps are able to fine-tune customized adapters on resource-limited devices, achieving 12.7% accuracy improvement and 6.6× memory reduction compared with operating the original foundation LLM.

The demand for machine learning (ML) model training on edge devices is escalating due to data privacy and personalized service needs. However, we observe that current on-device model training is hampered by the under-utilization of on-device data, due to low training throughput, limited storage and diverse data importance. To improve data resource utilization, we propose a two-stage data selection framework {\sf Titan} to select the most important data batch from streaming data for model training with guaranteed efficiency and effectiveness. Specifically, in the first stage, {\sf Titan} filters out a candidate dataset with potentially high importance in a coarse-grained manner.In the second stage of fine-grained selection, we propose a theoretically optimal data selection strategy to identify the data batch with the highest model performance improvement to current training round. To further enhance time-and-resource efficiency, {\sf Titan} leverages a pipeline to co-execute data selection and model training, and avoids resource conflicts by exploiting idle computing resources. We evaluate {\sf Titan} on real-world edge devices and three representative edge computing tasks with diverse models and data modalities. Empirical results demonstrate that {\sf Titan} achieves up to $43\%$ reduction in training time and $6.2\%$ increase in final accuracy with minor system overhead, such as data processing delay, memory footprint and energy consumption.

Online continual learning (CL) is becoming a mainstream paradigm to learn incrementally from task streams without forgetting previously learned knowledge. However, the current online CL primarily focuses on learning performance, such as avoiding catastrophic forgetting, neglecting the critical demands of system performance, such as real-time inference. As a result, the performance of real-time inference in online CL degrades significantly due to frequent data distribution variations and time-consuming model adaptation. In this work, we propose ELITE, an online CL framework with device-cloud collaboration, to realize on-device real-time inference on time-varying task streams with performance guarantee. To realize on-device real-time inference in online CL, ELITE features a new design of the model zoo comprising various pre-trained models with the assistance of the cloud, and proposes a task-oriented on-device model selection to quickly retrieve the best-fit models instead of performing time-consuming model retraining. To prevent performance degradation on new tasks not available in the cloud, we introduces a latency-aware on-device model fine-tuning strategy to adapt to new tasks with an accuracy-latency trade-off, and dynamically updates the model zoo to enhance ELITE. Extensive evaluations on five real-world datasets have been conducted, and the results demonstrate that ELITE consistently outperforms the state-of-art solutions, improving the accuracy by 16.3% on average and reducing the response latency by up to 1.98 times.

In modern mobile applications, users frequently encounter various new contexts, necessitating on-device continual learning (CL) to ensure consistent model performance. While existing research predominantly focused on developing lightweight CL frameworks, we identify that data scarcity is a critical bottleneck for on-device CL. In this work, we explore the potential of leveraging abundant cloud-side data to enrich scarce on-device data, and propose a private, efficient and effective data enrichment framework Delta. Specifically, Delta first introduces a directory dataset to decompose the data enrichment problem into device-side and cloud-side sub-problems without sharing sensitive data. Next, Delta proposes a soft data matching strategy to effectively solve the device-side sub-problem with sparse user data, and an optimal data sampling scheme for cloud server to retrieve the most suitable dataset for enrichment with low computational complexity. Further, Delta refines the data sampling scheme by jointly considering the impact of enriched data on both new and past contexts, mitigating the catastrophic forgetting issue from a new aspect. Comprehensive experiments across four typical mobile computing tasks with varied data modalities demonstrate that Delta could enhance the overall model accuracy by an average of 15.1%, 12.4%, 1.1% and 5.6% for visual, IMU, audio and textual tasks compared with few-shot CL, and consistently reduce the communication costs by over 90% compared to federated CL.

Machine learning (ML) models have been deployed in mobile networks to deal with massive data from different layers to enable automated network management. To overcome high communication cost and severe privacy concerns of centralized ML, federated learning (FL) has been proposed to achieve distributed ML among numerous networked devices. While the computation and communication limitation has been widely studied, the impact of limited storage of mobile devices on the performance of FL is still not explored. Without an effective data selection policy to filter the massive streaming networked data on devices, classical FL can suffer from much longer model training time ($4\times$) and dramatic inference accuracy reduction ($7\%$), observed in our experiments. In this work, we take the first step to consider the online data selection for FL with limited on-device storage. We first define a new data valuation metric for data selection in FL with theoretical guarantee for simultaneously accelerating model convergence and enhancing final accuracy. We further design ODE, an Online Data sElection framework for FL, to coordinate networked devices to store valuable data samples collaboratively. Experimental results on one industrial dataset and three public datasets show the remarkable advantages of ODE over the state-of-the-art approaches. Particularly, on the industrial dataset, ODE achieves as high as$2.5\times$speedup of training time and$6\%$increase in final accuracy, and is robust to various factors in practical environments.

Music plagiarism detection is gaining more and more attention due to the popularity of music production and society's emphasis on intellectual property. We aim to find fine-grained plagiarism in music pairs since conventional methods are coarse-grained and cannot match real-life scenarios. Considering that there is no sizeable dataset designed for the music plagiarism task, we establish a large-scale simulated dataset, named Music Plagiarism Detection Dataset (MPD-Set) under the guidance and expertise of researchers from national-level professional institutions in the field of music. MPD-Set considers diverse music plagiarism cases found in real life from the melodic, rhythmic, and tonal levels respectively. Further, we establish a Real-life Dataset for evaluation, where all plagiarism pairs are real cases. To detect the fine-grained plagiarism pairs effectively, we propose a graph-based method called Bipatite Melody Matching Detector (BMM-Det), which formulates the problem as a max matching problem in the bipartite graph. Experimental results on both the simulated and Real-life Datasets demonstrate that BMM-Det outperforms the existing plagiarism detection methods, and is robust to common plagiarism cases like transpositions, pitch shifts, duration variance, and melody change. Datasets and source code are open-sourced at https://github.com/xuan301/BMMDet_MPDSet.

Machine learning models have been deployed in mobile networks to deal with massive data from different layers to enable automated network management and intelligence on devices. To overcome high communication cost and severe privacy concerns of centralized machine learning, federated learning (FL) has been proposed to achieve distributed machine learning among networked devices. While the computation and communication limitation has been widely studied, the impact of on-device storage on the performance of FL is still not explored. Without an effective data selection policy to filter the massive streaming data on devices, classical FL can suffer from much longer model training time (4 ×) and significant inference accuracy reduction (7%), observed in our experiments. In this work, we take the first step to consider the online data selection for FL with limited on-device storage. We first define a new data valuation metric for data evaluation and selection in FL with theoretical guarantees for speeding up model convergence and enhancing final model accuracy, simultaneously. We further design ODE, a framework of Online Data sElection for FL, to coordinate networked devices to store valuable data samples. Experimental results on one industrial dataset and three public datasets show the remarkable advantages of ODE over the state-of-the-art approaches. Particularly, on the industrial dataset, ODE achieves as high as 2.5 × speedup of training time and 6% increase in inference accuracy, and is robust to various factors in practical environments.