On The Dynamic Ensemble Selection for TinyML-based Systems -- a Preliminary Study

• URL: http://arxiv.org/abs/2509.25218v1
• Date: Mon, 22 Sep 2025 18:35:35 GMT
• Title: On The Dynamic Ensemble Selection for TinyML-based Systems -- a Preliminary Study
• Authors: Tobiasz Puslecki, Krzysztof Walkowiak,
• Abstract summary: Recent progress in TinyML technologies triggers the need to address the challenge of balancing inference time and classification quality.<n>This study examines a DES-Clustering approach for a multi-class computer vision task within TinyML systems.<n> Experiments have shown that a larger pool of classifiers for dynamic selection improves classification accuracy, and thus leads to an increase in average inference time on the TinyML device.
• Score: 0.9553819152637493
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The recent progress in TinyML technologies triggers the need to address the challenge of balancing inference time and classification quality. TinyML systems are defined by specific constraints in computation, memory and energy. These constraints emphasize the need for specialized optimization techniques when implementing Machine Learning (ML) applications on such platforms. While deep neural networks are widely used in TinyML, the exploration of Dynamic Ensemble Selection (DES) methods is also beneficial. This study examines a DES-Clustering approach for a multi-class computer vision task within TinyML systems. This method allows for adjusting classification accuracy, thereby affecting latency and energy consumption per inference. We implemented the TinyDES-Clustering library, optimized for embedded system limitations. Experiments have shown that a larger pool of classifiers for dynamic selection improves classification accuracy, and thus leads to an increase in average inference time on the TinyML device.

Related papers

• Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs [54.70676039314542]
  We present the first systematic study on quantizing diffusion-based language models.<n>We identify the presence of activation outliers, characterized by abnormally large activation values.<n>We implement state-of-the-art PTQ methods and conduct a comprehensive evaluation across multiple task types and model variants.
  arXiv  Detail & Related papers  (2025-08-20T17:59:51Z)
• Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey [69.45421620616486]
  This work presents the first structured taxonomy and analysis of discrete tokenization methods designed for large language models (LLMs)<n>We categorize 8 representative VQ variants that span classical and modern paradigms and analyze their algorithmic principles, training dynamics, and integration challenges with LLM pipelines.<n>We identify key challenges including codebook collapse, unstable gradient estimation, and modality-specific encoding constraints.
  arXiv  Detail & Related papers  (2025-07-21T10:52:14Z)
• LOP: Learning Optimal Pruning for Efficient On-Demand MLLMs Scaling [52.1366057696919]
  LOP is an efficient neural pruning framework that learns optimal pruning strategies from the target pruning constraint.<n>LOP approach trains autoregressive neural networks (NNs) to directly predict layer-wise pruning strategies adaptive to the target pruning constraint.<n> Experimental results show that LOP outperforms state-of-the-art pruning methods in various metrics while achieving up to three orders of magnitude speedup.
  arXiv  Detail & Related papers  (2025-06-15T12:14:16Z)
• Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Need [83.10178754323955]
  Few-shot learning enables models to generalize from only a few labeled examples.<n>We propose the Unbiased Max-Min Embedding Classification (UMMEC) Method, which addresses the key challenges in few-shot learning.<n>Our method significantly improves classification performance with minimal labeled data, advancing the state-of-the-art in annotatedL.
  arXiv  Detail & Related papers  (2025-03-28T07:23:07Z)
• Fast Data Aware Neural Architecture Search via Supernet Accelerated Evaluation [0.43550340493919387]
  Tiny machine learning (TinyML) promises to revolutionize fields such as healthcare, environmental monitoring, and industrial maintenance.<n>The complex optimizations required for successful TinyML deployment continue to impede its widespread adoption.<n>We propose a new state-of-the-art Data Aware Neural Architecture Search technique and demonstrate its effectiveness on the novel TinyML VisionWake' dataset.
  arXiv  Detail & Related papers  (2025-02-18T09:51:03Z)
• LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment [12.80921403367322]
  Large Language Models (LLMs) demonstrate exceptional performance across various domains.<n> Quantization techniques, which reduce the size and memory requirements of LLMs, are effective for deploying LLMs on resource-limited edge devices.<n>We propose Layer-Specific Adaptive Quantization (LSAQ), a system for adaptive quantization and dynamic deployment of LLMs based on layer importance.
  arXiv  Detail & Related papers  (2024-12-24T03:43:15Z)
• HAFLQ: Heterogeneous Adaptive Federated LoRA Fine-tuned LLM with Quantization [55.972018549438964]
  Federated fine-tuning of pre-trained Large Language Models (LLMs) enables task-specific adaptation across diverse datasets while preserving privacy.<n>We propose HAFLQ (Heterogeneous Adaptive Federated Low-Rank Adaptation Fine-tuned LLM with Quantization), a novel framework for efficient and scalable fine-tuning of LLMs in heterogeneous environments.<n> Experimental results on the text classification task demonstrate that HAFLQ reduces memory usage by 31%, lowers communication cost by 49%, improves accuracy by 50%, and achieves faster convergence compared to the baseline method.
  arXiv  Detail & Related papers  (2024-11-10T19:59:54Z)
• Improved Diversity-Promoting Collaborative Metric Learning for Recommendation [127.08043409083687]
  Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems. This paper focuses on a challenging scenario where a user has multiple categories of interests. We propose a novel method called textitDiversity-Promoting Collaborative Metric Learning (DPCML)
  arXiv  Detail & Related papers  (2024-09-02T07:44:48Z)
• TinySV: Speaker Verification in TinyML with On-device Learning [2.356162747014486]
  This paper introduces a new type of adaptive TinyML solution that can be used in tasks, such as the presented textitTiny Speaker Verification (TinySV) The proposed TinySV solution relies on a two-layer hierarchical TinyML solution comprising Keyword Spotting and Adaptive Speaker Verification module. We evaluate the effectiveness and efficiency of the proposed TinySV solution on a dataset collected expressly for the task and tested the proposed solution on a real-world IoT device.
  arXiv  Detail & Related papers  (2024-06-03T17:27:40Z)
• On-device Online Learning and Semantic Management of TinyML Systems [8.183732025472766]
  This study aims to bridge the gap between prototyping single TinyML models and developing reliable TinyML systems in production. We propose online learning to enable training on constrained devices, adapting local models towards the latest field conditions. We present semantic management for the joint management of models and devices at scale.
  arXiv  Detail & Related papers  (2024-05-13T10:03:34Z)
• A review of TinyML [0.0]
  The TinyML concept for embedded machine learning attempts to push such diversity from usual high-end approaches to low-end applications. TinyML is a rapidly expanding interdisciplinary topic at the convergence of machine learning, software, and hardware. This paper explores how TinyML can benefit a few specific industrial fields, its obstacles, and its future scope.
  arXiv  Detail & Related papers  (2022-11-05T06:02:08Z)

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.