LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms

• URL: http://arxiv.org/abs/2311.11420v1
• Date: Sun, 19 Nov 2023 20:39:35 GMT
• Title: LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms
• Abstract summary: Continual Learning (CL) allows applications such as user personalization and household robots to learn on the fly and adapt to context. LifeLearner is a hardware-aware meta learning system that drastically optimize system resources. LifeLearner achieves near-optimal CL performance, falling short by only 2.8% on accuracy compared to an Oracle baseline.
• Score: 17.031135153343502
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual Learning (CL) allows applications such as user personalization and household robots to learn on the fly and adapt to context. This is an important feature when context, actions, and users change. However, enabling CL on resource-constrained embedded systems is challenging due to the limited labeled data, memory, and computing capacity. In this paper, we propose LifeLearner, a hardware-aware meta continual learning system that drastically optimizes system resources (lower memory, latency, energy consumption) while ensuring high accuracy. Specifically, we (1) exploit meta-learning and rehearsal strategies to explicitly cope with data scarcity issues and ensure high accuracy, (2) effectively combine lossless and lossy compression to significantly reduce the resource requirements of CL and rehearsal samples, and (3) developed hardware-aware system on embedded and IoT platforms considering the hardware characteristics. As a result, LifeLearner achieves near-optimal CL performance, falling short by only 2.8% on accuracy compared to an Oracle baseline. With respect to the state-of-the-art (SOTA) Meta CL method, LifeLearner drastically reduces the memory footprint (by 178.7x), end-to-end latency by 80.8-94.2%, and energy consumption by 80.9-94.2%. In addition, we successfully deployed LifeLearner on two edge devices and a microcontroller unit, thereby enabling efficient CL on resource-constrained platforms where it would be impractical to run SOTA methods and the far-reaching deployment of adaptable CL in a ubiquitous manner. Code is available at https://github.com/theyoungkwon/LifeLearner.

Related papers

• Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning [0.05402395391469584]
  We introduce embedder-centric learning (ECL), a framework that unifies four different online learning scenarios.<n>ECL can be deployed on resource-constrained devices across four real-world use cases.<n>We present first hardware demonstrations of ZSL with semantic data and ICL operating at micro-to-milliwatt power budgets.
  arXiv  Detail & Related papers  (2026-07-31T12:37:48Z)
• Leveraging ECRAM for Edge Continual Learning [8.240867084753257]
  In-memory computing (IMC) can curtail this waste and make continual learning feasible at the edge computation.<n>We propose CLASP, which is the first end-to-end system with IMC acceleration for continual learning.<n>We show that CLASP with ECRAM approaches the accuracy of IMC training, while delivering a speedup of 67x and energy savings of 132x for learning without forgetting.
  arXiv  Detail & Related papers  (2026-07-22T02:00:22Z)
• MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild [74.7263562191605]
  Large language model (LLM) agents are increasingly used for complex tasks.<n>Existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining.<n>We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills.
  arXiv  Detail & Related papers  (2026-03-17T22:30:30Z)
• MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning [47.195830952416294]
  We introduce an innovative approach named Meta Post-Refinement (MePo) for PTMs-based general continual learning (GCL)<n>MePo constructs pseudo task sequences from pretraining data and develops a bi-level meta-learning paradigm to refine the pretrained backbone.<n>MePo serves as a plug-in strategy that achieves significant performance gains across a variety of GCL benchmarks and pretrained checkpoints.
  arXiv  Detail & Related papers  (2026-02-08T12:15:35Z)
• UniErase: Towards Balanced and Precise Unlearning in Language Models [69.04923022755547]
  Large language models (LLMs) require iterative updates to address the outdated information problem.<n>UniErase is a novel unlearning framework that demonstrates precision and balanced performances between knowledge unlearning and ability retaining.
  arXiv  Detail & Related papers  (2025-05-21T15:53:28Z)
• MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices [17.800367605774863]
  We develop an end-to-end Meta-CL benchmark framework for edge devices to evaluate system overheads and investigate trade-offs among performance, computational costs, and memory requirements. Our results reveal that while many Meta-CL methods enable to learn new classes for both image and audio modalities, they impose significant computational and memory costs on edge devices. Also, we find that pre-training and meta-training procedures based on source data before deployment improve Meta-CL performance.
  arXiv  Detail & Related papers  (2025-03-31T19:31:49Z)
• Memory Is Not the Bottleneck: Cost-Efficient Continual Learning via Weight Space Consolidation [55.77835198580209]
  Continual learning (CL) has traditionally emphasized minimizing exemplar memory usage, assuming that memory is the primary bottleneck.<n>This paper re-examines CL under a more realistic setting with sufficient exemplar memory, where the system can retain a representative portion of past data.<n>We find that, under this regime, stability improves due to reduced forgetting, but plasticity diminishes as the model becomes biased toward prior tasks and struggles to adapt to new ones.
  arXiv  Detail & Related papers  (2025-02-11T05:40:52Z)
• Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices [26.939025828011196]
  The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. We propose a Constraint-aware Adaptive Exact Unlearning System at the network Edge (CAUSE) to enable exact unlearning on resource-constrained devices.
  arXiv  Detail & Related papers  (2024-10-14T03:28:09Z)
• Efficient Continual Learning with Low Memory Footprint For Edge Device [6.818488262543482]
  This paper proposes a compact algorithm called LightCL to overcome the forgetting problem of Continual Learning. We first propose two new metrics of learning plasticity and memory stability to seek generalizability during CL. In the experimental comparison, LightCL outperforms other SOTA methods in delaying forgetting and reduces at most $textbf6.16$times$$ memory footprint.
  arXiv  Detail & Related papers  (2024-07-15T08:52:20Z)
• Learn it or Leave it: Module Composition and Pruning for Continual Learning [48.07144492109635]
  MoCL-P is a lightweight continual learning method that balances knowledge integration and computational overhead. Our evaluation shows that MoCL-P achieves state-of-the-art performance and improves parameter efficiency by up to three times.
  arXiv  Detail & Related papers  (2024-06-26T19:18:28Z)
• CRSFL: Cluster-based Resource-aware Split Federated Learning for Continuous Authentication [5.636155173401658]
  Split Learning (SL) and Federated Learning (FL) have emerged as promising technologies for training a decentralized Machine Learning (ML) model. We propose combining these technologies to address the continuous authentication challenge while protecting user privacy.
  arXiv  Detail & Related papers  (2024-05-12T06:08:21Z)
• Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation [123.4883806344334]
  We study a realistic Continual Learning setting where learning algorithms are granted a restricted computational budget per time step while training. We apply this setting to large-scale semi-supervised Continual Learning scenarios with sparse label rates. Our extensive analysis and ablations demonstrate that DietCL is stable under a full spectrum of label sparsity, computational budget, and various other ablations.
  arXiv  Detail & Related papers  (2024-04-19T10:10:39Z)
• Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly [62.473245910234304]
  This paper takes a hardware-centric approach to explore how Large Language Models can be brought to modern edge computing systems. We provide a micro-level hardware benchmark, compare the model FLOP utilization to a state-of-the-art data center GPU, and study the network utilization in realistic conditions.
  arXiv  Detail & Related papers  (2023-10-04T20:27:20Z)
• FLEdge: Benchmarking Federated Machine Learning Applications in Edge Computing Systems [61.335229621081346]
  Federated Learning (FL) has become a viable technique for realizing privacy-enhancing distributed deep learning on the network edge. In this paper, we propose FLEdge, which complements existing FL benchmarks by enabling a systematic evaluation of client capabilities.
  arXiv  Detail & Related papers  (2023-06-08T13:11:20Z)
• SparCL: Sparse Continual Learning on the Edge [43.51885725281063]
  We propose a novel framework called Sparse Continual Learning(SparCL) to enable cost-effective continual learning on edge devices. SparCL achieves both training acceleration and accuracy preservation through the synergy of three aspects: weight sparsity, data efficiency, and gradient sparsity.
  arXiv  Detail & Related papers  (2022-09-20T05:24:48Z)
• Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors [68.8204255655161]
  This paper compares four state-of-the-art algorithms in two real applications: gesture recognition based on accelerometer data and image classification. Our results confirm these systems' reliability and the feasibility of deploying them in tiny-memory MCUs.
  arXiv  Detail & Related papers  (2022-09-01T17:05:20Z)
• A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays [66.62377866022221]
  Latent Replay-based Continual Learning (CL) techniques enable online, serverless adaptation in principle. We introduce a HW/SW platform for end-to-end CL based on a 10-core FP32-enabled parallel ultra-low-power processor. Our results show that by combining these techniques, continual learning can be achieved in practice using less than 64MB of memory.
  arXiv  Detail & Related papers  (2021-10-20T11:01:23Z)
• LIMITS: Lightweight Machine Learning for IoT Systems with Resource Limitations [8.647853543335662]
  We present the novel open source framework LIghtweight Machine learning for IoT Systems (LIMITS) LIMITS applies a platform-in-the-loop approach explicitly considering the actual compilation toolchain of the target IoT platform. We apply and validate LIMITS in two case studies focusing on cellular data rate prediction and radio-based vehicle classification.
  arXiv  Detail & Related papers  (2020-01-28T06:34:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.