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

14 Sep 2019  ·  Sawyer Birnbaum, Volodymyr Kuleshov, Zayd Enam, Pang Wei Koh, Stefano Ermon ·

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

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Audio Super-Resolution Piano U-Net + TFiLM Log-Spectral Distance 2 # 2
Audio Super-Resolution Voice Bank corpus (VCTK) U-Net + TFiLM Log-Spectral Distance 2.5 # 2