REVIEW 7 cited by
CAN: Feature Co-Action for Click-Through Rate Prediction
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Feature interaction has been recognized as an important problem in machine learning, which is also very essential for click-through rate (CTR) prediction tasks. In recent years, Deep Neural Networks (DNNs) can automatically learn implicit nonlinear interactions from original sparse features, and therefore have been widely used in industrial CTR prediction tasks. However, the implicit feature interactions learned in DNNs cannot fully retain the complete representation capacity of the original and empirical feature interactions (e.g., cartesian product) without loss. For example, a simple attempt to learn the combination of feature A and feature B <A, B> as the explicit cartesian product representation of new features can outperform previous implicit feature interaction models including factorization machine (FM)-based models and their variations. In this paper, we propose a Co-Action Network (CAN) to approximate the explicit pairwise feature interactions without introducing too many additional parameters. More specifically, giving feature A and its associated feature B, their feature interaction is modeled by learning two sets of parameters: 1) the embedding of feature A, and 2) a Multi-Layer Perceptron (MLP) to represent feature B. The approximated feature interaction can be obtained by passing the embedding of feature A through the MLP network of feature B. We refer to such pairwise feature interaction as feature co-action, and such a Co-Action Network unit can provide a very powerful capacity to fitting complex feature interactions. Experimental results on public and industrial datasets show that CAN outperforms state-of-the-art CTR models and the cartesian product method. Moreover, CAN has been deployed in the display advertisement system in Alibaba, obtaining 12\% improvement on CTR and 8\% on Revenue Per Mille (RPM), which is a great improvement to the business.
Forward citations
Cited by 7 Pith papers
-
LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders
LONGER combines global tokens, token merging with inner transformers, and hybrid causal attention to model sequences of length 10,000 end-to-end, outperforming strong baselines offline and online at ByteDance.
-
Balancing Efficiency and Effectiveness: An LLM-Infused Approach for Optimized CTR Prediction
MSD, an LLM-distilled multi-level semantic CTR framework, reports offline AUC gains and online CTR/CPM gains on Meituan sponsored search.
-
InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction
A bidirectional, interleaved interaction module with a separate Cross Arch for selective summarization improves CTR prediction over unidirectional fusion baselines by small margins on public and industrial data.
-
Measure Domain's Gap: A Similar Domain Selection Principle for Multi-Domain Recommendation
A prototype-based distance measure plus an epsilon-greedy bandit selects per-domain subsets of source domains, improving multi-domain recommendation accuracy by reducing negative transfer.
-
Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction
MIRRN improves CTR prediction by retrieving interests at target, local, and global granularities and refining them with a target-aware position encoding and a multi-head Fourier transformer, achieving up to 1.35% rela...
-
MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
A three-stage MoE variant of MLoRA improves multi-domain CTR prediction on sparse Taobao data but not on denser Movielens splits.
-
Scaling New Frontiers: Insights into Large Recommendation Models
Deep HSTU models tend to improve recall, ranking, multi-behavior, and multi-domain performance on public data, while GPT and SASRec fail to scale, though the evidence lacks error bars.
Discussion (0). Continue with ORCID to comment.