Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations

TL;DR

Temporal FiLM introduces a recurrent-based modulation technique that enhances convolutional models' ability to capture long-range dependencies in sequential data, improving learning speed and accuracy across various tasks.

Contribution

It proposes TFiLM, a novel architectural component that expands receptive fields of convolutional models using recurrent neural networks for better long-range dependency modeling.

Findings

Significantly improves learning speed and accuracy.

Effective on text classification and audio super-resolution tasks.

Minimal computational overhead.

Abstract

Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning. Feed-forward convolutional models capture only feature interactions within finite receptive fields while recurrent architectures can be slow and difficult to train due to vanishing gradients. Here, we propose Temporal Feature-Wise Linear Modulation (TFiLM) -- a novel architectural component inspired by adaptive batch normalization and its extensions -- that uses a recurrent neural network to alter the activations of a convolutional model. This approach expands the receptive field of convolutional sequence models with minimal computational overhead. Empirically, we find that TFiLM significantly improves the learning speed and accuracy of feed-forward neural networks on a range of generative and discriminative learning tasks, including text classification and audio super-resolution