A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention
This addresses the challenge of handling variable-length sequences in bioinformatics and other domains, offering a scalable and interpretable method, though it is incremental as it builds on existing optimal transport and attention concepts.
The paper tackles the problem of learning on sets of features, particularly for pooling in long biological sequences with varying sizes and dependencies, by introducing a trainable optimal transport embedding for feature aggregation. It achieves state-of-the-art results in protein fold recognition and chromatin profile detection, with promising applications in natural language processing.
We address the problem of learning on sets of features, motivated by the need of performing pooling operations in long biological sequences of varying sizes, with long-range dependencies, and possibly few labeled data. To address this challenging task, we introduce a parametrized representation of fixed size, which embeds and then aggregates elements from a given input set according to the optimal transport plan between the set and a trainable reference. Our approach scales to large datasets and allows end-to-end training of the reference, while also providing a simple unsupervised learning mechanism with small computational cost. Our aggregation technique admits two useful interpretations: it may be seen as a mechanism related to attention layers in neural networks, or it may be seen as a scalable surrogate of a classical optimal transport-based kernel. We experimentally demonstrate the effectiveness of our approach on biological sequences, achieving state-of-the-art results for protein fold recognition and detection of chromatin profiles tasks, and, as a proof of concept, we show promising results for processing natural language sequences. We provide an open-source implementation of our embedding that can be used alone or as a module in larger learning models at https://github.com/claying/OTK.