Neural Attentive Circuits

November 28, 2022


Recent work has seen the development of general purpose neural architectures that can be trained to perform tasks across diverse data modalities. General purpose models typically make few assumptions about the underlying data-structure and are known to perform well in the large-data regime. At the same time, there has been growing interest in modular neural architectures that represent the data using sparsely interacting modules. These models can be more robust out-of-distribution, computationally efficient, and capable of sample-efficient adaptation to new data. However, they tend to make domain-specific assumptions about the data, and present challenges in how module behavior (i.e., parameterization) and connectivity (i.e., their layout) can be jointly learned. In this work, we introduce a general purpose, yet modular neural architecture called Neural Attentive Circuits (NACs) that jointly learns the parameterization and a sparse connectivity of neural modules without using domain knowledge. NACs are best understood as the combination of two systems that are jointly trained end-to-end: one that determines the module configuration and the other that executes it on an input. We demonstrate qualitatively that NACs learn diverse and meaningful module configurations on the NLVR2 dataset without additional supervision. Quantitatively, we show that by incorporating modularity in this way, NACs improve upon a strong non-modular baseline in terms of low-shot adaptation on CIFAR and CUBs dataset by about 10%, and OOD robustness on Tiny ImageNet-R by about 2.5%. Further, we find that NACs can achieve an 8x speedup at inference time while losing less than 3% performance. Finally, we find NACs to yield competitive results on diverse data modalities spanning point-cloud classification, symbolic processing and text-classification from ASCII bytes, thereby confirming its general purpose nature.

Download the Paper


Written by

Nicolas Ballas

Bernhard Schölkopf

Chris Pal

Francesco Locatello

Li Erran

Martin Weiss

Nasim Rahaman

Yoshua Bengio



Research Topics

Core Machine Learning

Related Publications

February 15, 2024


Revisiting Feature Prediction for Learning Visual Representations from Video

Adrien Bardes, Quentin Garrido, Xinlei Chen, Michael Rabbat, Yann LeCun, Mido Assran, Nicolas Ballas, Jean Ponce

February 15, 2024

January 09, 2024


Accelerating a Triton Fused Kernel for W4A16 Quantized Inference with SplitK Work Decomposition

Less Wright, Adnan Hoque

January 09, 2024

January 06, 2024



Learning to bid and rank together in recommendation systems

Geng Ji, Wentao Jiang, Jiang Li, Fahmid Morshed Fahid, Zhengxing Chen, Yinghua Li, Jun Xiao, Chongxi Bao, Zheqing (Bill) Zhu

January 06, 2024

November 13, 2023


Mechanic: A Learning Rate Tuner

Aaron Defazio, Ashok Cutkosky, Harsh Mehta

November 13, 2023

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.