Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction

TL;DR

This paper introduces LAIN, a novel framework that dynamically balances modeling of long and short user behavior sequences in CTR prediction, improving accuracy especially for short-sequence users.

Contribution

LAIN is a new, plug-and-play method that incorporates sequence length as a conditioning signal to enhance CTR models' ability to handle diverse sequence lengths.

Findings

Consistently improves CTR prediction performance across benchmarks.

Achieves up to 1.15% AUC gain and 2.25% log loss reduction.

Significantly enhances short-sequence user prediction accuracy.

Abstract

User behavior sequences in modern recommendation systems exhibit significant length heterogeneity, ranging from sparse short-term interactions to rich long-term histories. While longer sequences provide more context, we observe that increasing the maximum input sequence length in existing CTR models paradoxically degrades performance for short-sequence users due to attention polarization and length imbalance in training data. To address this, we propose LAIN(Length-Adaptive Interest Network), a plug-and-play framework that explicitly incorporates sequence length as a conditioning signal to balance long- and short-sequence modeling. LAIN consists of three lightweight components: a Spectral Length Encoder that maps length into continuous representations, Length-Conditioned Prompting that injects global contextual cues into both long- and short-term behavior branches, and Length-Modulated Attention that adaptively adjusts attention sharpness based on sequence length. Extensive experiments on three real-world benchmarks across five strong CTR backbones show that LAIN consistently improves overall performance, achieving up to 1.15% AUC gain and 2.25% log loss reduction. Notably, our method significantly improves accuracy for short-sequence users without sacrificing longsequence effectiveness. Our work offers a general, efficient, and deployable solution to mitigate length-induced bias in sequential recommendation.