DLF: Enhancing Explicit-Implicit Interaction via Dynamic Low-Order-Aware Fusion for CTR Prediction

TL;DR

The paper introduces DLF, a novel framework that dynamically fuses explicit and implicit feature interactions to improve CTR prediction accuracy, addressing limitations of existing models in information sharing and low-order signal preservation.

Contribution

It proposes a new dynamic fusion framework with RLI and NAF modules to better balance low- and high-order interactions in CTR prediction models.

Findings

DLF achieves state-of-the-art results on public CTR datasets.

The framework effectively balances low- and high-order feature interactions.

Experimental results show improved model expressiveness and robustness.

Abstract

Click-through rate (CTR) prediction is a critical task in online advertising and recommender systems, relying on effective modeling of feature interactions. Explicit interactions capture predefined relationships, such as inner products, but often suffer from data sparsity, while implicit interactions excel at learning complex patterns through non-linear transformations but lack inductive biases for efficient low-order modeling. Existing two-stream architectures integrate these paradigms but face challenges such as limited information sharing, gradient imbalance, and difficulty preserving low-order signals in sparse CTR data. We propose a novel framework, Dynamic Low-Order-Aware Fusion (DLF), which addresses these limitations through two key components: a Residual-Aware Low-Order Interaction Network (RLI) and a Network-Aware Attention Fusion Module (NAF). RLI explicitly preserves low-order signals while mitigating redundancy from residual connections, and NAF dynamically integrates explicit and implicit representations at each layer, enhancing information sharing and alleviating gradient imbalance. Together, these innovations balance low-order and high-order interactions, improving model expressiveness. Extensive experiments on public datasets demonstrate that DLF achieves state-of-the-art performance in CTR prediction, addressing key limitations of existing models. The implementation is publicly available at https://github.com/USTC-StarTeam/DLF.