Model Compression and AutoML for Efficient Click-Through Rate Prediction
Name
Gschwind-gschwind-meng-eecs-2021-thesis.pdf
Description
Thesis PDF
Size
1.5 MB
Format
Adobe PDF
Checksum (MD5)
daff535a9b8b6968e46981e9025490b2
Author(s)
Gschwind, Katharina
Advisor(s)
Han, Song
Date Issued
June 2021
Publisher
Massachusetts Institute of Technology
Abstract
Novel machine learning architectures can adeptly learn to predict user response for recommender systems. However, these model architectures are often effective at the cost of large computational, and memory, cost. This limits their ability to run on edge devices with smaller hardwares, such as smartphones, which is a popular use case for recommender systems. We address this issue in this thesis by studying how compression of recommender system models can significantly reduce model computation cost, and edge device runtime, while preserving prediction accuracy. Furthermore, we present a new compression-based AutoML method for feature set generation in architectures which incorporate explicit feature interactions. This works as a tool to build efficient recommender system models, and is applicable to many state of the art model designs. Applying this AutoML shows initial gains in model performance.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
