Learning Soft Sparse Shapes for Efficient Time-Series Classification

TL;DR

SoftShape introduces a novel soft shape sparsification and learning framework for time-series classification, enhancing efficiency and interpretability by merging less important subsequences and learning intra- and inter-shape patterns.

Contribution

The paper proposes SoftShape, a new model that uses soft shape sparsification and learning blocks to improve time-series classification efficiency and interpretability.

Findings

SoftShape outperforms state-of-the-art methods in accuracy.

SoftShape provides interpretable shape representations.

The model effectively merges less important subsequences without losing information.

Abstract

Shapelets are discriminative subsequences (or shapes) with high interpretability in time series classification. Due to the time-intensive nature of shapelet discovery, existing shapelet-based methods mainly focus on selecting discriminative shapes while discarding others to achieve candidate subsequence sparsification. However, this approach may exclude beneficial shapes and overlook the varying contributions of shapelets to classification performance. To this end, we propose a Soft sparse Shapes (SoftShape) model for efficient time series classification. Our approach mainly introduces soft shape sparsification and soft shape learning blocks. The former transforms shapes into soft representations based on classification contribution scores, merging lower-scored ones into a single shape to retain and differentiate all subsequence information. The latter facilitates intra- and inter-shape temporal pattern learning, improving model efficiency by using sparsified soft shapes as inputs. Specifically, we employ a learnable router to activate a subset of class-specific expert networks for intra-shape pattern learning. Meanwhile, a shared expert network learns inter-shape patterns by converting sparsified shapes into sequences. Extensive experiments show that SoftShape outperforms state-of-the-art methods and produces interpretable results.