What is the purpose of using contrastive language-shapelets learning in DiffShape?

The purpose is to enhance the discriminative capacity of the learned shapelets by aligning their representations with textual description embeddings through contrastive learning. This alignment makes the shapelet features more class-relevant, which improves classification accuracy in semi-supervised settings where labeled data are scarce.

In DiffShape, contrastive language-shapelet learning uses textual descriptions derived from ground-truth labels and classifier pseudo-labels. A frozen language encoder converts those texts into embeddings, while a shapelet encoder maps both the initial and diffusion-generated shapelets into representation space. Contrastive learning then minimizes the distance between the shapelet representations and the language embeddings. This alignment steers the learned shapelets toward semantically meaningful, discriminative patterns, and the same shapelet representation is also fed into the classifier. Ablation results confirm that removing this language-shapelet alignment lowers classification performance, indicating that it plays a significant role in guiding shapelets to capture class-relevant features under label scarcity.