Tagged articles
feature interaction
12 articles · Page 1 of 1
HyFormer, a novel hybrid Transformer framework introduced by ByteDance’s TikTok search team, integrates sequence modeling and feature interaction into a unified alternating optimization process, enhancing representation power and scaling efficiency for ultra‑long user behavior sequences and high‑dimensional heterogeneous features, leading to significant offline and online performance gains.
AIHyFormerSequence Modeling
0 likes · 12 min read

This article reviews the latest academic advances in multimodal recommendation systems, covering background, system workflow, modal encoders, feature interaction (connection, fusion, filtering), feature enhancement, model optimization, and future research challenges.
AIfeature enhancementfeature interaction
0 likes · 18 min read

Researchers from Alibaba Cloud AI and Zhejiang University present AMFormer, a Transformer‑based model that incorporates arithmetic feature interaction, demonstrating superior fine‑grained modeling, sample efficiency, and generalization on synthetic and real‑world tabular datasets, establishing a new state‑of‑the‑art in deep tabular learning.
AMFormerTransformerdeep learning
0 likes · 12 min read

This article presents a memory‑driven architecture (HCNet and MemoNet) that equips recommendation models with scaling‑law characteristics by storing and retrieving arbitrary feature‑combination embeddings, evaluates multi‑hash codebooks, memory‑restoring strategies, key‑feature selection, and demonstrates significant offline and online performance gains.
Scaling Lawfeature interactionlarge language models
0 likes · 15 min read

This article reviews the development of CTR prediction models from early collaborative‑filtering methods to modern deep‑learning approaches, discusses core challenges such as feature interaction and continuous‑feature embedding, introduces recent Huawei solutions like AutoDis and ScaleFreeCTR for efficient large‑embedding training, and outlines future research directions.
Embeddingcontinuous featuresdistributed training
0 likes · 21 min read

This article reviews the evolution of recommendation models from early collaborative filtering to modern deep learning approaches, discusses core challenges such as CTR prediction, outlines user‑behavior and combination‑feature modeling techniques, introduces large‑embedding training and continuous‑feature embedding methods like AutoDis, and presents distributed training frameworks such as ScaleFreeCTR, concluding with future research directions.
CTR predictionEmbeddingdeep learning
0 likes · 21 min read

The Co‑Action Network replaces costly Cartesian‑product feature crossing with lightweight micro‑net‑based interaction units that share parameters across feature pairs, delivering comparable CTR prediction accuracy while cutting parameters to one‑tenth and boosting online latency, as proven in large‑scale advertising deployments.
Co-Action Networkfeature interactionrecommendation systems
0 likes · 22 min read

This article systematically reviews the evolution of click‑through‑rate (CTR) prediction models—from early distributed linear models like logistic regression, through automated feature engineering with GBDT+LR, various factorization‑machine variants, embedding‑MLP shallow modifications, dual‑tower combinations, and advanced explicit feature‑cross networks—highlighting each model’s structure, advantages, limitations, and comparative insights.
CTR predictionclick-through ratefactorization machines
0 likes · 28 min read

This article details the development and deployment of CAN (Co‑Action Net), a novel click‑through‑rate prediction model that captures item‑item co‑action via attention‑based slot embeddings, offering superior performance to Cartesian‑product methods while reducing parameter and serving costs.
CTR predictionCo-Action Netfeature interaction
0 likes · 14 min read

This article introduces the Deep Sparse Network (NON), a new deep neural architecture for recommendation systems that combines field‑wise networks, across‑field interaction networks, and an operation‑fusion network, and demonstrates its superior performance through extensive experiments and ablation studies.
CTR predictiondeep learningfeature interaction
0 likes · 14 min read

This article describes iQIYI’s dual‑DNN ranking architecture that combines a high‑capacity teacher network with a lightweight student network via online knowledge distillation, addressing the trade‑off between model effectiveness and inference efficiency in large‑scale recommendation systems.
CTR predictionRanking Modelsdual DNN
0 likes · 12 min read

iQIYI’s dual‑DNN ranking model uses an online teacher‑student knowledge‑distillation framework where a complex teacher DNN shares representations with a lightweight student DNN, enabling end‑to‑end training, large‑scale feature crossing, and substantially higher recommendation accuracy while cutting inference latency and model size.
CTR predictiondual DNNfeature interaction
0 likes · 15 min read
