Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
This addresses the need for efficient and effective models for set-structured data in domains like computer vision and machine learning, representing a novel method rather than an incremental improvement.
The paper tackles the problem of modeling permutation-invariant set-structured data in machine learning tasks like multiple instance learning and few-shot classification by introducing the Set Transformer, an attention-based neural network module that achieves state-of-the-art performance across various benchmarks.
Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set, models used to address them should be permutation invariant. We present an attention-based neural network module, the Set Transformer, specifically designed to model interactions among elements in the input set. The model consists of an encoder and a decoder, both of which rely on attention mechanisms. In an effort to reduce computational complexity, we introduce an attention scheme inspired by inducing point methods from sparse Gaussian process literature. It reduces the computation time of self-attention from quadratic to linear in the number of elements in the set. We show that our model is theoretically attractive and we evaluate it on a range of tasks, demonstrating the state-of-the-art performance compared to recent methods for set-structured data.