One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks

03/29/2021
by   Atish Agarwala, et al.
0

Can deep learning solve multiple tasks simultaneously, even when they are unrelated and very different? We investigate how the representations of the underlying tasks affect the ability of a single neural network to learn them jointly. We present theoretical and empirical findings that a single neural network is capable of simultaneously learning multiple tasks from a combined data set, for a variety of methods for representing tasks – for example, when the distinct tasks are encoded by well-separated clusters or decision trees over certain task-code attributes. More concretely, we present a novel analysis that shows that families of simple programming-like constructs for the codes encoding the tasks are learnable by two-layer neural networks with standard training. We study more generally how the complexity of learning such combined tasks grows with the complexity of the task codes; we find that combining many tasks may incur a sample complexity penalty, even though the individual tasks are easy to learn. We provide empirical support for the usefulness of the learning bounds by training networks on clusters, decision trees, and SQL-style aggregation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/23/2017

Neural Decision Trees

In this paper we propose a synergistic melting of neural networks and de...
research
12/07/2017

End-to-end Learning of Deterministic Decision Trees

Conventional decision trees have a number of favorable properties, inclu...
research
02/01/2022

Exploring layerwise decision making in DNNs

While deep neural networks (DNNs) have become a standard architecture fo...
research
01/04/2022

Time and space complexity of deterministic and nondeterministic decision trees

In this paper, we study arbitrary infinite binary information systems ea...
research
09/02/2019

Bayesian Neural Tree Models for Nonparametric Regression

Frequentist and Bayesian methods differ in many aspects, but share some ...
research
01/16/2020

Extracting more from boosted decision trees: A high energy physics case study

Particle identification is one of the core tasks in the data analysis pi...
research
01/13/2022

Exact learning for infinite families of concepts

In this paper, based on results of exact learning, test theory, and roug...

Please sign up or login with your details

Forgot password? Click here to reset