HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series

• URL: http://arxiv.org/abs/2510.25785v1
• Date: Tue, 28 Oct 2025 14:15:45 GMT
• Title: HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series
• Authors: Simon A. Lee, Cyrus Tanade, Hao Zhou, Juhyeon Lee, Megha Thukral, Minji Han, Rachel Choi, Md Sazzad Hissain Khan, Baiying Lu, Migyeong Gwak, Mehrab Bin Morshed, Viswam Nathan, Md Mahbubur Rahman, Li Zhu, Subramaniam Venkatraman, Sharanya Arcot Desai,
• Abstract summary: We introduce HiMAE (Hierarchical Masked Autoencoder), a self supervised framework that combines masked autoencoding with a hierarchical convolutional encoder decoder.<n>HiMAE produces multi resolution embeddings that enable systematic evaluation of which temporal scales carry predictive signal.
• Score: 12.476150662404741
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Wearable sensors provide abundant physiological time series, yet the principles governing their predictive utility remain unclear. We hypothesize that temporal resolution is a fundamental axis of representation learning, with different clinical and behavioral outcomes relying on structure at distinct scales. To test this resolution hypothesis, we introduce HiMAE (Hierarchical Masked Autoencoder), a self supervised framework that combines masked autoencoding with a hierarchical convolutional encoder decoder. HiMAE produces multi resolution embeddings that enable systematic evaluation of which temporal scales carry predictive signal, transforming resolution from a hyperparameter into a probe for interpretability. Across classification, regression, and generative benchmarks, HiMAE consistently outperforms state of the art foundation models that collapse scale, while being orders of magnitude smaller. HiMAE is an efficient representation learner compact enough to run entirely on watch, achieving sub millisecond inference on smartwatch class CPUs for true edge inference. Together, these contributions position HiMAE as both an efficient self supervised learning method and a discovery tool for scale sensitive structure in wearable health.

Related papers

• Robust Representation Learning in Masked Autoencoders [2.599882743586164]
  Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood.<n>This work started as an attempt to understand the strong downstream classification performance of MAE.
  arXiv  Detail & Related papers  (2026-02-03T13:48:34Z)
• HyM-UNet: Synergizing Local Texture and Global Context via Hybrid CNN-Mamba Architecture for Medical Image Segmentation [3.976000861085382]
  HyM-UNet is designed to synergize the local feature extraction capabilities of CNNs with the efficient global modeling capabilities of Mamba.<n>To bridge the semantic gap between the encoder and the decoder, we propose a Mamba-Guided Fusion Skip Connection.<n>The results demonstrate that HyM-UNet significantly outperforms existing state-of-the-art methods in terms of Dice coefficient and IoU.
  arXiv  Detail & Related papers  (2025-11-22T09:02:06Z)
• Time-Aware Feature Selection: Adaptive Temporal Masking for Stable Sparse Autoencoder Training [0.47745223151611654]
  We introduce Adaptive Temporal Masking (ATM), a novel training approach that adjusts feature selection by tracking activation magnitudes, frequencies, and reconstruction contributions to compute importance scores that evolve over time.<n> ATM achieves substantially lower absorption scores compared to existing methods like TopK and JumpReLU SAEs, while maintaining excellent reconstruction quality.
  arXiv  Detail & Related papers  (2025-10-09T23:12:51Z)
• Towards Efficient General Feature Prediction in Masked Skeleton Modeling [59.46799426434277]
  We propose a novel General Feature Prediction framework (GFP) for efficient mask skeleton modeling.<n>Our key innovation is replacing conventional low-level reconstruction with high-level feature prediction that spans from local motion patterns to global semantic representations.
  arXiv  Detail & Related papers  (2025-09-03T18:05:02Z)
• Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning [81.02648336552421]
  We propose a Multi-Constraint Consistency Learning approach to facilitate the staged enhancement of the encoder and decoder.<n>Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder.<n> Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-23T03:21:33Z)
• Interpreting CLIP with Hierarchical Sparse Autoencoders [8.692675181549117]
  Matryoshka SAE (MSAE) learns hierarchical representations at multiple granularities simultaneously.<n>MSAE establishes a new state-of-the-art frontier between reconstruction quality and sparsity for CLIP.
  arXiv  Detail & Related papers  (2025-02-27T22:39:13Z)
• MAUCell: An Adaptive Multi-Attention Framework for Video Frame Prediction [0.0]
  We introduce the Multi-Attention Unit (MAUCell) which combines Generative Adrative Networks (GANs) and attention mechanisms to improve video prediction.<n>The new design system maintains equilibrium between temporal continuity and spatial accuracy to deliver reliable video prediction.
  arXiv  Detail & Related papers  (2025-01-28T14:52:10Z)
• UGMAE: A Unified Framework for Graph Masked Autoencoders [67.75493040186859]
  We propose UGMAE, a unified framework for graph masked autoencoders. We first develop an adaptive feature mask generator to account for the unique significance of nodes. We then design a ranking-based structure reconstruction objective joint with feature reconstruction to capture holistic graph information.
  arXiv  Detail & Related papers  (2024-02-12T19:39:26Z)
• Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence [56.092059713922744]
  We show that using high-level contextualized features as prediction targets can achieve superior performance. Specifically, we propose Skeleton2vec, a simple and efficient self-supervised 3D action representation learning framework. Our proposed Skeleton2vec outperforms previous methods and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2024-01-01T12:08:35Z)
• Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations [4.666056064419346]
  The efficient coding hypothesis proposes that the response properties of sensory systems are adapted to the statistics of their inputs. While elegant, information theoretic properties are notoriously difficult to measure in practical settings or to employ as objective functions in optimization. Here we outline the assumptions that allow manifold capacity to be optimized directly, yielding Maximum Manifold Capacity Representations (MMCR)
  arXiv  Detail & Related papers  (2023-03-06T17:26:30Z)
• STIP: A SpatioTemporal Information-Preserving and Perception-Augmented Model for High-Resolution Video Prediction [78.129039340528]
  We propose a Stemporal Information-Preserving and Perception-Augmented Model (STIP) to solve the above two problems. The proposed model aims to preserve thetemporal information for videos during the feature extraction and the state transitions. Experimental results show that the proposed STIP can predict videos with more satisfactory visual quality compared with a variety of state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-06-09T09:49:04Z)
• Autoregressive Hidden Markov Models with partial knowledge on latent space applied to aero-engines prognostics [2.179313476241343]
  This paper describes an Autoregressive Partially-hidden Markov model (ARPHMM) for fault detection and prognostics of equipments based on sensors' data. We show how to apply this model to estimate the remaining useful life based on health indicators.
  arXiv  Detail & Related papers  (2021-05-01T10:23:22Z)
• Deep Autoencoding Topic Model with Scalable Hybrid Bayesian Inference [55.35176938713946]
  We develop deep autoencoding topic model (DATM) that uses a hierarchy of gamma distributions to construct its multi-stochastic-layer generative network. We propose a Weibull upward-downward variational encoder that deterministically propagates information upward via a deep neural network, followed by a downward generative model. The efficacy and scalability of our models are demonstrated on both unsupervised and supervised learning tasks on big corpora.
  arXiv  Detail & Related papers  (2020-06-15T22:22:56Z)

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.