Towards An Efficient LLM Training Paradigm for CTR Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Allen, Cai, Renqin, He, Yun, Yu, Hanchao, Qian, Jing, Li, Rui, Wang, Qifan, Caverlee, James
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915199649316864
author Lin, Allen
Cai, Renqin
He, Yun
Yu, Hanchao
Qian, Jing
Li, Rui
Wang, Qifan
Caverlee, James
author_facet Lin, Allen
Cai, Renqin
He, Yun
Yu, Hanchao
Qian, Jing
Li, Rui
Wang, Qifan
Caverlee, James
contents Large Language Models (LLMs) have demonstrated tremendous potential as the next-generation ranking-based recommendation system. Many recent works have shown that LLMs can significantly outperform conventional click-through-rate (CTR) prediction approaches. Despite such promising results, the computational inefficiency inherent in the current training paradigm makes it particularly challenging to train LLMs for ranking-based recommendation tasks on large datasets. To train LLMs for CTR prediction, most existing studies adopt the prevalent ''sliding-window'' paradigm. Given a sequence of $m$ user interactions, a unique training prompt is constructed for each interaction by designating it as the prediction target along with its preceding $n$ interactions serving as context. In turn, the sliding-window paradigm results in an overall complexity of $O(mn^2)$ that scales linearly with the length of user interactions. Consequently, a direct adoption to train LLMs with such strategy can result in prohibitively high training costs as the length of interactions grows. To alleviate the computational inefficiency, we propose a novel training paradigm, namely Dynamic Target Isolation (DTI), that structurally parallelizes the training of $k$ (where $k >> 1$) target interactions. Furthermore, we identify two major bottlenecks - hidden-state leakage and positional bias overfitting - that limit DTI to only scale up to a small value of $k$ (e.g., 5) then propose a computationally light solution to effectively tackle each. Through extensive experiments on three widely adopted public CTR datasets, we empirically show that DTI reduces training time by an average of $\textbf{92%}$ (e.g., from $70.5$ hrs to $5.31$ hrs), without compromising CTR prediction performance.
format Preprint
id arxiv_https___arxiv_org_abs_2503_01001
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards An Efficient LLM Training Paradigm for CTR Prediction
Lin, Allen
Cai, Renqin
He, Yun
Yu, Hanchao
Qian, Jing
Li, Rui
Wang, Qifan
Caverlee, James
Information Retrieval
Large Language Models (LLMs) have demonstrated tremendous potential as the next-generation ranking-based recommendation system. Many recent works have shown that LLMs can significantly outperform conventional click-through-rate (CTR) prediction approaches. Despite such promising results, the computational inefficiency inherent in the current training paradigm makes it particularly challenging to train LLMs for ranking-based recommendation tasks on large datasets. To train LLMs for CTR prediction, most existing studies adopt the prevalent ''sliding-window'' paradigm. Given a sequence of $m$ user interactions, a unique training prompt is constructed for each interaction by designating it as the prediction target along with its preceding $n$ interactions serving as context. In turn, the sliding-window paradigm results in an overall complexity of $O(mn^2)$ that scales linearly with the length of user interactions. Consequently, a direct adoption to train LLMs with such strategy can result in prohibitively high training costs as the length of interactions grows. To alleviate the computational inefficiency, we propose a novel training paradigm, namely Dynamic Target Isolation (DTI), that structurally parallelizes the training of $k$ (where $k >> 1$) target interactions. Furthermore, we identify two major bottlenecks - hidden-state leakage and positional bias overfitting - that limit DTI to only scale up to a small value of $k$ (e.g., 5) then propose a computationally light solution to effectively tackle each. Through extensive experiments on three widely adopted public CTR datasets, we empirically show that DTI reduces training time by an average of $\textbf{92%}$ (e.g., from $70.5$ hrs to $5.31$ hrs), without compromising CTR prediction performance.
title Towards An Efficient LLM Training Paradigm for CTR Prediction
topic Information Retrieval
url https://arxiv.org/abs/2503.01001