mlsanityData to 7 Oct 2026

Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences

arXiv 2603.21508 ↗First posted 23 Mar 2026cs.LG cs.AI cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

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 1.33x-3.93x during daytime and 1.43x-4.53x at night.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 79 references that are in the map. First posted on arXiv 23 Mar 2026.

Builds on

21 of 79 references.

References · 21

  1. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  2. 2016Wide & Deep Learning for Recommender Systemscited by 745
  3. 2023Data-centric Artificial Intelligence: A Surveycited by 202
  4. 2020PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruningcited by 75
  5. 2021DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusioncited by 56
  6. 2016Feature Selection: A Data Perspectivecited by 50
  7. 2019PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devicescited by 48
  8. 2018A First Look at Deep Learning Apps on Smartphonescited by 47
  9. 2019PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfigurationcited by 41
  10. 2022Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloadingcited by 29
  11. 2021Smart at what cost? Characterising Mobile Deep Neural Networks in the wildcited by 25
  12. 2019On Application of Learning to Rank for E-Commerce Searchcited by 24
9 more
  1. 2023LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookupcited by 19
  2. 2023AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environmentscited by 19
  3. 2016Variational Information Maximization for Feature Selectioncited by 7
  4. 2022To Store or Not? Online Data Selection for Federated Learning with Limited Storagecited by 7
  5. 2025FedConv: A Learning-on-Model Paradigm for Heterogeneous Federated Clientscited by 7
  6. 2024Delta: A Cloud-assisted Data Enrichment Framework for On-Device Continual Learningcited by 6
  7. 2017MobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPUcited by 5
  8. 2020Active Feature Selection for the Mutual Information Criterioncited by 4
  9. 2025Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Appscited by 1

Built on by

Not cited yet.