HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation

• URL: http://arxiv.org/abs/2605.02278v1
• Date: Mon, 04 May 2026 07:09:39 GMT
• Title: HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation
• Abstract summary: Time series imputation benefits from leveraging cross-feature correlations.<n>Existing attention-based methods re-discover feature relationships at each layer.<n>We propose HELIX, which assigns each feature a learnable feature identity.
• Score: 14.247555410538148
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Time series imputation benefits from leveraging cross-feature correlations, yet existing attention-based methods re-discover feature relationships at each layer, lacking persistent anchors to maintain consistent representations. To address this, we propose HELIX, which assigns each feature a learnable feature identity, a persistent embedding that captures intrinsic semantic properties throughout the network. Unlike graph-based methods that rely on predefined topology and assume homogeneous spatial relationships, HELIX learns arbitrary feature dependencies end-to-end from temporal co-variation, naturally handling datasets where features mix spatial locations with semantic variables. Integrated with hybrid temporal-feature attention, HELIX achieves the state-of-the-art performance, surpassing all 16 baselines on 5 public datasets across 21 experimental settings in our evaluation. Furthermore, our mechanistic analysis reveals that HELIX aligns learned feature identities and dependencies with latent physical and semantic structure progressively across layers, demonstrating that it more effectively translates cross-feature structure into imputation accuracy.

Related papers

• Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis [55.78822230833247]
  We present Inter-X++, a comprehensive and large-scale benchmark designed to empower versatile HHI analysis.<n>Inter-X++ provides 11,388 high-fidelity interaction sequences and over 8.1M frames, featuring precise whole-body movements and detailed finger articulations.<n>We propose OpenHHI, a single and unified HHI representation and modeling framework that jointly optimize interaction reconstruction and semantic understanding.
  arXiv  Detail & Related papers  (2026-08-20T17:51:48Z)
• H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers [2.7415651415305597]
  We introduce H-Sets, a novel framework for discovering and attributing higher-order feature interactions in image classifiers.<n>We attribute each set with IDG-Vis, a set-level extension of Integrated Directional Gradients that integrates directional gradients along pixel-space paths.<n> Evaluations across VGG, ResNet, DenseNet and MobileNet models on ImageNet and CUB datasets show that H-Sets generate more interpretable and faithful saliency maps.
  arXiv  Detail & Related papers  (2026-04-23T20:03:17Z)
• Integrating Temporal and Structural Context in Graph Transformers for Relational Deep Learning [6.780460717949915]
  We introduce a temporal subgraph sampler that enhances global context by retrieving nodes beyond the immediate neighborhood.<n>We also propose Graph Perceiver (RGP), a graph transformer architecture for relational deep learning.<n>RGP delivers state-of-the-art performance, offering a general and scalable solution for relational deep learning.
  arXiv  Detail & Related papers  (2025-11-06T17:08:21Z)
• Unlocking Multi-Modal Potentials for Link Prediction on Dynamic Text-Attributed Graphs [28.533930417703715]
  Dynamic Text-Attributed Graphs (DyTAGs) are a novel graph paradigm that captures evolving temporal events (edges) alongside rich textual attributes.<n>MoMent is a multi-modal model that explicitly models, integrates, and aligns each modality to learn node representations for link prediction.<n>Experiments show that MoMent achieves up to 17.28% accuracy improvement and up to 31x speed-up against eight baselines.
  arXiv  Detail & Related papers  (2025-02-27T00:49:44Z)
• Graph Structure Learning for Spatial-Temporal Imputation: Adapting to Node and Feature Scales [29.499581329290805]
  We introduce the multi-scale Graph Structure Learning framework for spatial-temporal Imputation (GSLI)<n>Our framework encompasses node-scale graph structure learning to cater to the distinct global spatial correlations of different features.<n> integrated with prominence modeling, our framework emphasizes nodes and features with greater significance in the imputation process.
  arXiv  Detail & Related papers  (2024-12-24T16:34:50Z)
• Leveraging 2D Information for Long-term Time Series Forecasting with Vanilla Transformers [55.475142494272724]
  Time series prediction is crucial for understanding and forecasting complex dynamics in various domains. We introduce GridTST, a model that combines the benefits of two approaches using innovative multi-directional attentions. The model consistently delivers state-of-the-art performance across various real-world datasets.
  arXiv  Detail & Related papers  (2024-05-22T16:41:21Z)
• Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation [64.85974098314344]
  Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. Inherently, object pairs and their relationships enjoy spatial co-occurrence correlations within each image and temporal consistency/transition correlations across different images. We propose a spatial-temporal knowledge-embedded transformer (STKET) that incorporates the prior spatial-temporal knowledge into the multi-head cross-attention mechanism.
  arXiv  Detail & Related papers  (2023-09-23T02:40:28Z)
• Unified and Dynamic Graph for Temporal Character Grouping in Long Videos [31.192044026127032]
  Video temporal character grouping locates appearing moments of major characters within a video according to their identities. Recent works have evolved from unsupervised clustering to graph-based supervised clustering. We present a unified and dynamic graph (UniDG) framework for temporal character grouping.
  arXiv  Detail & Related papers  (2023-08-27T13:22:55Z)
• Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition [50.932864767867365]
  We propose a framework that consists of two complementary regularizations to achieve spatial and semantic consistency for each attribute. Based on the precise attribute locations, we propose a semantic consistency regularization to extract intrinsic and discriminative semantic features. Results show that the proposed method performs favorably against state-of-the-art methods without increasing parameters.
  arXiv  Detail & Related papers  (2021-09-13T03:36:44Z)
• Spatio-Temporal Representation Factorization for Video-based Person Re-Identification [55.01276167336187]
  We propose Spatio-Temporal Representation Factorization module (STRF) for re-ID. STRF is a flexible new computational unit that can be used in conjunction with most existing 3D convolutional neural network architectures for re-ID. We empirically show that STRF improves performance of various existing baseline architectures while demonstrating new state-of-the-art results.
  arXiv  Detail & Related papers  (2021-07-25T19:29:37Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)

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.