Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Apps

2025-10-15

AI Summary

To address the high storage overhead of user behavioral logs in embedded ML-based mobile applications—which increases response latency and app abandonment rates—this paper proposes AdaLog. Methodologically, AdaLog innovatively formulates feature-level redundancy elimination as a maximum-weight hypergraph matching problem; introduces a virtual hash attribute allocation mechanism coupled with an incremental update strategy for adaptive log compression; and integrates hierarchical optimization with physically dense log sharding. Evaluated on real-world applications, AdaLog reduces log volume by 19%–44%, incurs only 2 seconds of inference latency and 15 MB memory overhead, and significantly improves storage efficiency and system responsiveness—while preserving model accuracy and meeting real-time constraints.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Machine learning (ML) models are increasingly integrated into modern mobile apps to enable personalized and intelligent services. These models typically rely on rich input features derived from historical user behaviors to capture user intents. However, as ML-driven services become more prevalent, recording necessary user behavior data imposes substantial storage cost on mobile apps, leading to lower system responsiveness and more app uninstalls. To address this storage bottleneck, we present AdaLog, a lightweight and adaptive system designed to improve the storage efficiency of user behavior log in ML-embedded mobile apps, without compromising model inference accuracy or latency. We identify two key inefficiencies in current industrial practices of user behavior log: (i) redundant logging of overlapping behavior data across different features and models, and (ii) sparse storage caused by storing behaviors with heterogeneous attribute descriptions in a single log file. To solve these issues, AdaLog first formulates the elimination of feature-level redundant data as a maximum weighted matching problem in hypergraphs, and proposes a hierarchical algorithm for efficient on-device deployment. Then, AdaLog employs a virtually hashed attribute design to distribute heterogeneous behaviors into a few log files with physically dense storage. Finally, to ensure scalability to dynamic user behavior patterns, AdaLog designs an incremental update mechanism to minimize the I/O operations needed for adapting outdated behavior log. We implement a prototype of AdaLog and deploy it into popular mobile apps in collaboration with our industry partner. Evaluations on real-world user data show that AdaLog reduces behavior log size by 19% to 44% with minimal system overhead (only 2 seconds latency and 15 MB memory usage), providing a more efficient data foundation for broader adoption of on-device ML.

Problem

• Reduces redundant logging of overlapping user behavior data across features
• Addresses sparse storage from heterogeneous attribute descriptions in logs
• Minimizes storage overhead while maintaining ML model accuracy and latency

Innovation

• Hypergraph matching eliminates feature-level redundant logging
• Virtually hashed attributes create dense storage files
• Incremental updates minimize I/O for dynamic behavior patterns