Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting

June 03, 2026 ยท Grace Period ยท ๐Ÿ› AAAI 2026 AI4TS Workshop

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Balthazar Courvoisier, Tristan Cazenave arXiv ID 2606.04833 Category cs.LG: Machine Learning Cross-listed cs.AI Citations 0 Venue AAAI 2026 AI4TS Workshop
Abstract
Initially developed for natural language processing, Transformer architectures and attention mechanisms are now central to a wide range of deep learning models, including applications in time series forecasting. A standard attention mechanism, however, implicitly assumes homophilic interactions, limiting its ability to model data with positive and negative dependencies, such as time series. In this work, we introduce the Signed Dual Attention, a novel attention formulation that captures both positive and negative relational patterns without additional parameters. By leveraging a dual message-passing scheme inspired by correlation structures, Signed Dual Attention propagates both supportive and contrastive information within a single shared block, effectively achieving the expressiveness of two head attention without additional parameters. This module can be seamlessly integrated into existing architectures and can yield performance gains in certain situations, requiring signed relational modeling. This approach opens a pathway toward more expressive and parameter-efficient transformers.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning