DynInt: Dynamic Interaction Modeling for Large-scale Click-Through Rate Prediction

TL;DR

DynInt introduces a dynamic, data-dependent approach to modeling feature interactions in large-scale CTR prediction, enhancing the capacity of neural networks to adapt interactions per instance for improved performance.

Contribution

The paper proposes DynInt, a novel extension of PIN that models dynamic feature interactions using instance-aware gating and parameter generation, addressing static interaction limitations.

Findings

DynInt outperforms state-of-the-art models on real-world datasets.

Dynamic interaction modeling improves CTR prediction accuracy.

The model demonstrates efficiency and effectiveness in large-scale applications.

Abstract

Learning feature interactions is the key to success for the large-scale CTR prediction in Ads ranking and recommender systems. In industry, deep neural network-based models are widely adopted for modeling such problems. Researchers proposed various neural network architectures for searching and modeling the feature interactions in an end-to-end fashion. However, most methods only learn static feature interactions and have not fully leveraged deep CTR models' representation capacity. In this paper, we propose a new model: DynInt. By extending Polynomial-Interaction-Network (PIN), which learns higher-order interactions recursively to be dynamic and data-dependent, DynInt further derived two modes for modeling dynamic higher-order interactions: dynamic activation and dynamic parameter. In dynamic activation mode, we adaptively adjust the strength of learned interactions by instance-aware activation gating networks. In dynamic parameter mode, we re-parameterize the parameters by different formulations and dynamically generate the parameters by instance-aware parameter generation networks. Through instance-aware gating mechanism and dynamic parameter generation, we enable the PIN to model dynamic interaction for potential industry applications. We implement the proposed model and evaluate the model performance on real-world datasets. Extensive experiment results demonstrate the efficiency and effectiveness of DynInt over state-of-the-art models.