Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising

TL;DR

This paper introduces Field-weighted Factorization Machines (FwFMs), a memory-efficient model for CTR prediction that outperforms traditional FFMs with significantly fewer parameters, achieving comparable or better accuracy.

Contribution

The paper proposes FwFMs, a novel model that reduces parameter count in field-aware interactions, maintaining high prediction performance in CTR tasks.

Findings

FwFMs use only 4% of FFM parameters.

FwFMs achieve 0.92% and 0.47% AUC lift over FFMs.

FwFMs maintain competitive accuracy with fewer parameters.

Abstract

Click-through rate (CTR) prediction is a critical task in online display advertising. The data involved in CTR prediction are typically multi-field categorical data, i.e., every feature is categorical and belongs to one and only one field. One of the interesting characteristics of such data is that features from one field often interact differently with features from different other fields. Recently, Field-aware Factorization Machines (FFMs) have been among the best performing models for CTR prediction by explicitly modeling such difference. However, the number of parameters in FFMs is in the order of feature number times field number, which is unacceptable in the real-world production systems. In this paper, we propose Field-weighted Factorization Machines (FwFMs) to model the different feature interactions between different fields in a much more memory-efficient way. Our experimental evaluations show that FwFMs can achieve competitive prediction performance with only as few as 4% parameters of FFMs. When using the same number of parameters, FwFMs can bring 0.92% and 0.47% AUC lift over FFMs on two real CTR prediction data sets.