Onboard Optimization and Learning: A Survey
Not on the map. Why?
Abstract (arXiv)
Onboard learning is a transformative approach in edge AI, enabling real-time data processing, decision-making, and adaptive model training directly on resource-constrained devices without relying on centralized servers. This paradigm is crucial for applications demanding low latency, enhanced privacy, and energy efficiency. However, onboard learning faces challenges such as limited computational resources, high inference costs, and security vulnerabilities. This survey explores a comprehensive range of methodologies that address these challenges, focusing on techniques that optimize model efficiency, accelerate inference, and support collaborative learning across distributed devices. Approaches for reducing model complexity, improving inference speed, and ensuring privacy-preserving computation are examined alongside emerging strategies that enhance scalability and adaptability in dynamic environments. By bridging advancements in hardware-software co-design, model compression, and decentralized learning, this survey provides insights into the current state of onboard learning to enable robust, efficient, and secure AI deployment at the edge.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 142 of its 310 references that are in the map. First posted on arXiv 7 May 2025.
Builds on
142 of 310 references.
References · 142
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
- 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2016Deep Learning with Differential Privacycited by 2,728
- 2016Learning without Forgettingcited by 2,496
- 2018DARTS: Differentiable Architecture Searchcited by 1,798
- 2020Knowledge Distillation: A Surveycited by 1,603
- 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
- 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,121
- 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
- 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
38 more
- 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
- 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
- 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 788
- 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
- 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
- 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 596
- 2023Splitwise: Efficient generative LLM inference using phase splittingcited by 558
- 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 527
- 2020Pruning neural networks without any data by iteratively conserving synaptic flowcited by 479
- 2021Compacter: Efficient Low-Rank Hypercomplex Adapter Layerscited by 460
- 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
- 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
- 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
- 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
- 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 402
- 2020iDLG: Improved Deep Leakage from Gradientscited by 382
- 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
- 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
- 2021Membership Inference Attacks on Machine Learning: A Surveycited by 321
- 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 316
- 2020SplitFed: When Federated Learning Meets Split Learningcited by 310
- 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 273
- 2020AdapterDrop: On the Efficiency of Adapters in Transformerscited by 224
- 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 222
- 2022Knowledge Distillation from A Stronger Teachercited by 208
- 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
- 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 202
- 2020Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluationcited by 188
- 2020Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPOcited by 186
- 2019Class-incremental Learning via Deep Model Consolidationcited by 173
- 2022Structured Pruning Learns Compact and Accurate Modelscited by 170
- 2022A Fast Post-Training Pruning Framework for Transformerscited by 162
- 2022On-Device Training Under 256KB Memorycited by 160
- 2019Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computingcited by 152
- 2020Training with Quantization Noise for Extreme Model Compressioncited by 145
- 2020Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Datacited by 125
- 2021MLPerf Tiny Benchmarkcited by 124
- 2017Distributed Deep Neural Networks over the Cloud, the Edge and End Devicescited by 120
50 most cited of 142 All 142 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.