DeepAI AI Chat
Log In Sign Up

A Parallel and Efficient Algorithm for Learning to Match

10/22/2014
by   Jingbo Shang, et al.
HUAWEI Technologies Co., Ltd.
Shanghai Jiao Tong University
University of Illinois at Urbana-Champaign
University of Washington
0

Many tasks in data mining and related fields can be formalized as matching between objects in two heterogeneous domains, including collaborative filtering, link prediction, image tagging, and web search. Machine learning techniques, referred to as learning-to-match in this paper, have been successfully applied to the problems. Among them, a class of state-of-the-art methods, named feature-based matrix factorization, formalize the task as an extension to matrix factorization by incorporating auxiliary features into the model. Unfortunately, making those algorithms scale to real world problems is challenging, and simple parallelization strategies fail due to the complex cross talking patterns between sub-tasks. In this paper, we tackle this challenge with a novel parallel and efficient algorithm for feature-based matrix factorization. Our algorithm, based on coordinate descent, can easily handle hundreds of millions of instances and features on a single machine. The key recipe of this algorithm is an iterative relaxation of the objective to facilitate parallel updates of parameters, with guaranteed convergence on minimizing the original objective function. Experimental results demonstrate that the proposed method is effective on a wide range of matching problems, with efficiency significantly improved upon the baselines while accuracy retained unchanged.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/14/2015

Online Matrix Factorization via Broyden Updates

In this paper, we propose an online algorithm to compute matrix factoriz...
12/03/2021

ALX: Large Scale Matrix Factorization on TPUs

We present ALX, an open-source library for distributed matrix factorizat...
03/31/2023

A fast Multiplicative Updates algorithm for Non-negative Matrix Factorization

Nonnegative Matrix Factorization is an important tool in unsupervised ma...
06/28/2019

Searching for Interaction Functions in Collaborative Filtering

Interaction function (IFC), which captures interactions among items and ...
07/19/2019

Neural Cross-Domain Collaborative Filtering with Shared Entities

Cross-Domain Collaborative Filtering (CDCF) provides a way to alleviate ...
05/15/2017

Probabilistic Matrix Factorization for Automated Machine Learning

In order to achieve state-of-the-art performance, modern machine learnin...
09/30/2020

Linear Matrix Factorization Embeddings for Single-objective Optimization Landscapes

Automated per-instance algorithm selection and configuration have shown ...

Code Repositories