Global and Local Topology-Aware Attention with Persistent Homology and Euler Biases for Time-Series Forecasting

• URL: http://arxiv.org/abs/2605.03163v1
• Date: Mon, 04 May 2026 21:19:12 GMT
• Title: Global and Local Topology-Aware Attention with Persistent Homology and Euler Biases for Time-Series Forecasting
• Abstract summary: Time series often encode predictive geometric structure, including connectivity, cycles, shell-like geometry, directional changes, and nonlinear neighborhoods.<n>We introduce a topology-aware attention framework that adds such structure to attention logits using persistent homology (H0-H2)<n>We evaluate guarded topology-aware variants across three architecture families: lightweight attention/Ridge, PatchTSTForRegression, and TimeSeriesTransformerForPrediction.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Scientific time series often encode predictive geometric structure, including connectivity, cycles, shell-like geometry, directional changes, and nonlinear neighborhoods, that standard dot-product attention does not explicitly represent. We introduce a topology-aware attention framework that adds such structure to attention logits using persistent homology (H0-H2), anchored Euler characteristic transforms, and kernel-Hilbert channels. A validation-gated local residual captures local topological signals, including a Zeng-style local H0 component, only when held-out validation data support the correction. Exact Vietoris-Rips computations and smooth topological surrogates are evaluated under a no-leakage protocol with train-only calibration, validation-only selection, and test-only reporting. We evaluate guarded topology-aware variants across three architecture families: lightweight attention/Ridge, PatchTSTForRegression, and TimeSeriesTransformerForPrediction. Experiments include synthetic benchmarks isolating higher-order topology and real datasets covering CO2, S&P 500 return-window geometry, and NASA IMS bearing degradation. The audit uses matched paired comparisons across seven dataset units, three random seeds, and three chronological splits, giving 63 paired units per architecture and 189 paired units overall. Topology-aware models show positive paired effects when geometry is predictive, with heterogeneous magnitude across datasets and architectures. Lightweight attention/Ridge improves in 46 of 63 units, with mean relative RMSE reduction of 12.5% and paired randomization p=7.2e-4; PatchTST improves in 33 units and retains the baseline in 20 units, with 23.5% reduction and p=3.5e-5; and TimeSeriesTransformer improves in 47 units, with 47.8% reduction and p<1e-4. The results support topology as a validation-selected, architecture-compatible inductive bias.

Related papers

• Curvature-Aware Radius Shrinkage for Adaptive Nearest Neighbor Classification [52.452902154360565]
  CARSANN is a geometry-driven framework that adapts the spatial support of each neighborhood according to local geometric complexity.<n>Experiments on more than 70 real-world OpenML datasets show that CARSANN consistently improves upon standard $k$-NN.
  arXiv  Detail & Related papers  (2026-08-27T19:19:07Z)
• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• Scaling Closed-Loop Feature Channel Configuration with LLMs [48.83701310501069]
  The analysis covers 2000 generated candidates from 8 complete cycles, yielding 462 verified CIFAR-100 evaluations after task and metadata filtering.<n>The best model reaches 0.3676 with 11.8M parameters, compared with an early high-performing model at 0.3144 with 166.5M parameters.<n>Non-power-of-two channel widths occur in 41.8% of verified candidates, and the strongest models share structured channelallocation patterns.
  arXiv  Detail & Related papers  (2026-07-07T22:31:53Z)
• RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting [83.06074370551887]
  A fixed context window is mismatched to the time-varying optimal look-back of non-stationary price processes.<n>We propose a Mixture-of-Experts framework designed to adaptively determine the temporal context for each input sample.<n> Experiments on cumulative log-return prediction (HS300, S&P500) and fund sales forecasting demonstrate that RAVEN achieves SOTA performances, improves Pearson correlation by 9.2% on HS300 and 20.2% on S&P500, and reduces MSE by 18.2% on fund sales forecasting.
  arXiv  Detail & Related papers  (2026-06-23T02:11:04Z)
• How Much Capacity Does EEG Denoising Need? Ultra-Compact Networks reveal Benchmark Saturation and Metric-Utility Gap [0.0]
  Deep learning EEG denoising architectures have scaled from tens of thousands to tens of millions of parameters, yet no prior study has isolated model capacity as the experimental variable.<n>We address both gaps by fixing architecture, loss, data split, and training recipe while sweeping only channel width from 1.05K to 40.26K parameters in a minimal depthwiseseparable convolutional U-Net.
  arXiv  Detail & Related papers  (2026-06-07T12:17:25Z)
• Efficient Hybrid CNN-GNN Architecture for Monocular Depth Estimation [0.0]
  We present GraphDepth, a monocular depth estimation architecture that integrates Graph Neural Networks (GNNs) within a convolutional encoder-decoder framework.<n>Our approach embeds efficient GraphSAGE layers at multiple scales of a ResNet-101 U-Net backbone.<n> Experiments on NYU Depth V2, WHU Aerial, ETH3D, and Mid-Air benchmarks demonstrate competitive accuracy within 4.6% of state-of-the-art transformers.
  arXiv  Detail & Related papers  (2026-05-11T09:21:04Z)
• DecompKAN: Decomposed Patch-KAN for Long-Term Time Series Forecasting [0.0]
  DecompKAN is a lightweight attention-free architecture that combines trend-residual decomposition, channel-wise patching, learned instance normalization, and B-spline Kolmogorov-Arnold Network (KAN) edge functions.
  arXiv  Detail & Related papers  (2026-04-27T02:29:35Z)
• ARCS: Autoregressive Circuit Synthesis with Topology-Aware Graph Attention and Spec Conditioning [0.0]
  ARCS produces complete, SPICE-simulatable designs in milliseconds rather than the minutes required by search-based methods.<n>For single-model inference, a topology-aware Graph Transformer with Best-of-3 candidate selection reaches 85% simulation validity in 97ms, over 600x faster than random search.
  arXiv  Detail & Related papers  (2026-03-30T23:14:08Z)
• Do Foundation Models Know Geometry? Probing Frozen Features for Continuous Physical Measurement [0.0]
  Vision-language models encode geometry that their text pathway fails to express.<n>LoRA fine-tuning (r=16, 2,000 images) narrows this gap to 6.5 degrees.<n>These findings enable a single frozen backbone to function as a multi-task geometric sensor.
  arXiv  Detail & Related papers  (2026-03-06T16:48:27Z)
• Resonant Sparse Geometry Networks [0.0]
  We introduce Resonant Sparse Geometry Networks (RSGN), a brain-inspired architecture with self-organizing sparse hierarchical input-dependent connectivity.<n> RSGN embeds computational nodes in learned hyperbolic space where connection strength decays with geodesic distance, achieving dynamic sparsity that adapts to each input.
  arXiv  Detail & Related papers  (2026-01-26T01:45:51Z)
• A Comprehensive Forecasting-Based Framework for Time Series Anomaly Detection: Benchmarking on the Numenta Anomaly Benchmark (NAB) [0.0]
  Time series anomaly detection is critical for modern digital infrastructures.<n>We present a forecasting-based framework unifying classical methods with deep learning architectures.<n>We conduct the first complete evaluation on the Numenta Anomaly Benchmark.
  arXiv  Detail & Related papers  (2025-10-13T08:31:42Z)
• AttentiveGRUAE: An Attention-Based GRU Autoencoder for Temporal Clustering and Behavioral Characterization of Depression from Wearable Data [46.262619407930266]
  We present AttentiveGRUAE, a novel attention-based gated recurrent unit (GRU) autoencoder designed for temporal clustering and prediction of outcome from longitudinal wearable data.<n>We evaluate AttentiveGRUAE on longitudinal sleep data from 372 participants (GLOBEM 2018-2019)<n>It demonstrates superior performance over baseline clustering, domain-aligned self-supervised, and ablated models in both clustering quality and depression classification.
  arXiv  Detail & Related papers  (2025-10-02T20:52:16Z)
• STQE: Spatial-Temporal Attribute Quality Enhancement for G-PCC Compressed Dynamic Point Clouds [52.435843736488145]
  We propose a spatial-temporal attribute quality enhancement (STQE) network that exploits both spatial and temporal correlations to improve the visual quality of compressed dynamic point clouds.<n>Our contributions include a recoloring-based motion compensation module that remaps reference attribute information to the current frame geometry to achieve precise inter-frame geometric alignment.<n>When applied to the latest G-PCC test model, STQE achieved improvements of 0.855 dB, 0.682 dB, and 0.828 dB in delta PSNR, with Bjontegaard Delta rate (BD-rate) reductions of -25.2%, -31.6%, and
  arXiv  Detail & Related papers  (2025-07-23T14:03:54Z)
• SpectralEarth: Training Hyperspectral Foundation Models at Scale [47.93167977587301]
  We introduce SpectralEarth, a large-scale multitemporal dataset designed to pretrain hyperspectral foundation models.<n>We pretrain a series of foundation models on SpectralEarth, integrating a spectral adapter into classical vision backbones.<n>In tandem, we construct nine downstream datasets for land-cover, crop-type mapping, and tree-species classification.
  arXiv  Detail & Related papers  (2024-08-15T22:55:59Z)
• Continual Spatio-Temporal Graph Convolutional Networks [87.86552250152872]
  We reformulating the Spatio-Temporal Graph Convolutional Neural Network as a Continual Inference Network. We observe up to 109x reduction in time complexity, on- hardware accelerations of 26x, and reductions in maximum allocated memory of 52% during online inference.
  arXiv  Detail & Related papers  (2022-03-21T14:23:18Z)
• Neural Distance Embeddings for Biological Sequences [43.07977514121458]
  We present NeuroSEED, a framework to embed sequences in geometric vector spaces. We show the effectiveness of the hyperbolic space that captures the hierarchical structure and provides an average 22% reduction in embedding RMSE. The proposed approaches display significant accuracy and/or runtime improvements on real-world datasets.
  arXiv  Detail & Related papers  (2021-09-20T17:30:58Z)

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.