Moderator : Frank Hutter
Yi Tay · Mostafa Dehghani · Vamsi Aribandi · Jai Gupta · Philip Pham · Zhen Qin · Dara Bahri · Da-Cheng Juan · Don Metzler
This paper proposes Omnidirectional Representations from Transformers (OMNINET). In OmniNet, instead of maintaining a strictly horizon-tal receptive field, each token is allowed to attend to all tokens in the entire network. This process can also be interpreted as a form of extreme or intensive attention mechanism that has the receptive field of the entire width and depth of the network. To this end, the omnidirectional attention is learned via a meta-learner, which is essentially another self-attention based model. In order to mitigate the computationally expensive costs of full receptive field attention, we leverage efficient self-attention models such as kernel-based, low-rank attention and/or Big Bird as the meta-learner. Extensive experiments are conducted on autoregressive language modeling(LM1B, C4), Machine Translation, Long Range Arena (LRA), and Image Recognition.The experiments show that OmniNet achieves considerable improvements across these tasks, including achieving state-of-the-art performance on LM1B,WMT’14 En-De/En-Fr, and Long Range Arena.Moreover, using omnidirectional representation in Vision Transformers leads to significant improvements on image recognition tasks on both few-shot learning and fine-tuning setups.
Jack Kosaian · Amar Phanishayee · Matthai Philipose · Debadeepta Dey · Rashmi Vinayak
Datacenter vision systems widely use small, specialized convolutional neural networks (CNNs) trained on specific tasks for high-throughput inference. These settings employ accelerators with massive computational capacity, but which specialized CNNs underutilize due to having low arithmetic intensity. This results in suboptimal application-level throughput and poor returns on accelerator investment. Increasing batch size is the only known way to increase both application-level throughput and accelerator utilization for inference, but yields diminishing returns; specialized CNNs poorly utilize accelerators even with large batch size. We propose FoldedCNNs, a new approach to CNN design that increases inference throughput and utilization beyond large batch size. FoldedCNNs rethink the structure of inputs and layers of specialized CNNs to boost arithmetic intensity: in FoldedCNNs, f images with C channels each are concatenated into a single input with fC channels and jointly classified by a wider CNN. Increased arithmetic intensity in FoldedCNNs increases the throughput and GPU utilization of specialized CNN inference by up to 2.5x and 2.8x, with accuracy close to the original CNN in most cases.
Victor Garcia Satorras · Emiel Hoogeboom · Max Welling
This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does not require computationally expensive higher-order representations in intermediate layers while it still achieves competitive or better performance. In addition, whereas existing methods are limited to equivariance on 3 dimensional spaces, our model is easily scaled to higher-dimensional spaces. We demonstrate the effectiveness of our method on dynamical systems modelling, representation learning in graph autoencoders and predicting molecular properties.
Javier Dehesa · Andrew Vidler · Julian Padget · Christof Lutteroth
We introduce a new neural network architecture that we call "grid-functioned" neural networks. It utilises a grid structure of network parameterisations that can be specialised for different subdomains of the problem, while maintaining smooth, continuous behaviour. The grid gives the user flexibility to prevent gross features from overshadowing important minor ones. We present a full characterisation of its computational and spatial complexity, and demonstrate its potential, compared to a traditional architecture, over a set of synthetic regression problems. We further illustrate the benefits through a real-world 3D skeletal animation case study, where it offers the same visual quality as a state-of-the-art model, but with lower computational complexity and better control accuracy.
Roshan Rao · Jason Liu · Robert Verkuil · Joshua Meier · John Canny · Pieter Abbeel · Tom Sercu · Alexander Rives
Unsupervised protein language models trained across millions of diverse sequences learn structure and function of proteins. Protein language models studied to date have been trained to perform inference from individual sequences. The longstanding approach in computational biology has been to make inferences from a family of evolutionarily related sequences by fitting a model to each family independently. In this work we combine the two paradigms. We introduce a protein language model which takes as input a set of sequences in the form of a multiple sequence alignment. The model interleaves row and column attention across the input sequences and is trained with a variant of the masked language modeling objective across many protein families. The performance of the model surpasses current state-of-the-art unsupervised structure learning methods by a wide margin, with far greater parameter efficiency than prior state-of-the-art protein language models.
Narsimha Reddy Chilkuri · Chris Eliasmith
Recently, a new recurrent neural network (RNN) named the Legendre Memory Unit (LMU) was proposed and shown to achieve state-of-the-art performance on several benchmark datasets. Here we leverage the linear time-invariant (LTI) memory component of the LMU to construct a simplified variant that can be parallelized during training (and yet executed as an RNN during inference), resulting in up to 200 times faster training. We note that our efficient parallelizing scheme is general and is applicable to any deep network whose recurrent components are linear dynamical systems. We demonstrate the improved accuracy of our new architecture compared to the original LMU and a variety of published LSTM and transformer networks across seven benchmarks. For instance, our LMU sets a new state-of-the-art result on psMNIST, and uses half the parameters while outperforming DistilBERT and LSTM models on IMDB sentiment analysis.