Beyond Similarity: Temporal Operator Attention for Time Series Analysis

TL;DR

This paper introduces Temporal Operator Attention (TOA), a novel framework augmenting attention with learnable sequence operators to better capture temporal dynamics in time series, outperforming traditional models.

Contribution

The paper formalizes the limitations of standard attention in time series and proposes TOA with stochastic regularization, improving performance across various benchmarks.

Findings

TOA enhances forecasting, anomaly detection, and classification accuracy.

Explicit operator learning improves modeling of oscillatory and signed transformations.

TOA achieves strong gains especially in reconstruction-heavy tasks.

Abstract

A persistent paradox in time-series forecasting is that structurally simple MLP and linear models often outperform high-capacity Transformers. We argue that this gap arises from a mismatch in the sequence-modeling primitive: while many time-series dynamics are governed by global temporal operators (e.g., filtering and harmonic structure), standard attention forms each output as a convex combination of inputs. This restricts its ability to represent signed and oscillatory transformations that are fundamental to temporal signal processing. We formalize this limitation as a simplex-constrained mixing bottleneck in softmax attention, which becomes especially restrictive for operator-driven time-series tasks. To address this, we propose $\textbf{Temporal Operator Attention (TOA)}$, a framework that augments attention with explicit, learnable sequence-space operators, enabling direct signed mixing across time while preserving input-dependent adaptivity. To make dense $N \times N$ operators practical, we introduce Stochastic Operator Regularization, a high-variance dropout mechanism that stabilizes training and prevents trivial memorization. Across forecasting, anomaly detection, and classification benchmarks, TOA consistently improves performance when integrated into standard backbones such as PatchTST and iTransformer, with particularly strong gains in reconstruction-heavy tasks. These results suggest that explicit operator learning is a key ingredient for effective time-series modeling.