Filters








6 Hits in 3.1 sec

AIM: Automatic Interaction Machine for Click-Through Rate Prediction [article]

Chenxu Zhu, Bo Chen, Weinan Zhang, Jincai Lai, Ruiming Tang, Xiuqiang He, Zhenguo Li, Yong Yu
<span title="2021-12-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Feature embedding learning and feature interaction modeling are two crucial components of deep models for Click-Through Rate (CTR) prediction.  ...  feature interaction in a learnable way; EDS component automatically searches proper embedding size for each feature.  ...  INTRODUCTION Click-Through Rate (CTR) prediction, which aims to predict the probability of the user clicking on the recommended items (e.g., music, advertisement), plays a core role in recommender systems  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.03318v2">arXiv:2111.03318v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/thzqyyf7ind2thvvnzbese3qda">fatcat:thzqyyf7ind2thvvnzbese3qda</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211112024052/https://arxiv.org/pdf/2111.03318v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/79/7f/797fcdf72f9ae0eb93b4564c635feac386f7a68a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.03318v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction [article]

Fuyuan Lyu, Xing Tang, Huifeng Guo, Ruiming Tang, Xiuqiang He, Rui Zhang, Xue Liu
<span title="2021-11-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Click-through rate prediction is one of the core tasks in commercial recommender systems. It aims to predict the probability of a user clicking a particular item given user and item features.  ...  feature interactions by explicitly viewing them as new features and assigning trainable embeddings; (3) factorized methods, which learn latent vectors for original features and implicitly model feature  ...  Index Terms-Click-through Rate Prediction, Feature Interaction, Recommendation, Neural Architecture Search I.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.01265v3">arXiv:2108.01265v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r6zwti5irndvfosgo2eca7kmji">fatcat:r6zwti5irndvfosgo2eca7kmji</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210829113236/https://arxiv.org/pdf/2108.01265v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/dc/7b/dc7b627bbbecf1d88a0905db96fc8185dcf8cb5f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.01265v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

AEFE: Automatic Embedded Feature Engineering for Categorical Features [article]

Zhenyuan Zhong, Jie Yang, Yacong Ma, Shoubin Dong, Jinlong Hu
<span title="2021-10-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The challenge of solving data mining problems in e-commerce applications such as recommendation system (RS) and click-through rate (CTR) prediction is how to make inferences by constructing combinatorial  ...  and then assist data analysts in discovering the feature importance for particular data mining tasks.  ...  Experiment Setting Datasets We conduct experiments on two public datasets and one private dataset, which are ad click-through rate prediction datasets.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.09770v1">arXiv:2110.09770v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rhiaopkft5hm3gulxfgwjdluqe">fatcat:rhiaopkft5hm3gulxfgwjdluqe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211021194814/https://arxiv.org/pdf/2110.09770v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d2/8e/d28e788b644c5091fb763029d471193548f7cf2c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.09770v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

TabGNN: Multiplex Graph Neural Network for Tabular Data Prediction [article]

Xiawei Guo, Yuhan Quan, Huan Zhao, Quanming Yao, Yong Li, Weiwei Tu
<span title="2021-08-20">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, existing works mainly focus on feature interactions and ignore sample relations, e.g., users with the same education level might have a similar ability to repay the debt.  ...  Tabular data prediction (TDP) is one of the most popular industrial applications, and various methods have been designed to improve the prediction performance.  ...  For example, in a click-through rate (CTR) prediction scenario, samples with the same user ID might be strongly related [27] , and therefore should be connected in the graph. • Beyond ID features, we  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.09127v1">arXiv:2108.09127v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7zojv4oayvfehhtcxiycvwmzfq">fatcat:7zojv4oayvfehhtcxiycvwmzfq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210830111424/https://arxiv.org/pdf/2108.09127v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/62/c5/62c5f0188be81ebff9292dc77056988fd366f044.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.09127v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Deep Learning for Click-Through Rate Estimation

Weinan Zhang, Jiarui Qin, Wei Guo, Ruiming Tang, Xiuqiang He
<span title="">2021</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence </i> &nbsp; <span class="release-stage">unpublished</span>
Click-through rate (CTR) estimation plays as a core function module in various personalized online services, including online advertising, recommender systems, and web search etc.  ...  Second, we concentrate on explicit feature interaction learning modules of deep CTR models.  ...  Weinan Zhang is supported by "New Generation of AI 2030" Major Project (2018AAA0100900) and National Natural Science Foundation of China (61772333, 61632017) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2021/636">doi:10.24963/ijcai.2021/636</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5dwiolb4y5f3vj6fohbpolax4a">fatcat:5dwiolb4y5f3vj6fohbpolax4a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210812235243/https://www.ijcai.org/proceedings/2021/0636.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b3/e2/b3e2a207cd3e7cf7ecb246a663c57e0fa362a0c8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2021/636"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction [article]

Fuyuan Lyu, Xing Tang, Huifeng Guo, Ruiming Tang, Xiuqiang He, Rui Zhang, Xue Liu
<span title="2021-08-01">2021</span>
Click-through rate prediction is one of the core tasks in commercial recommender systems. It aims to predict the probability of a user clicking a particular item given user and item features.  ...  feature interactions by explicitly viewing them as new features and assigning trainable embeddings; (3) factorized methods, which learn latent vectors for original features and implicitly model feature  ...  Index Terms-Click-through Rate Prediction, Feature Interaction, Recommendation, Neural Architecture Search I.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.48550/arxiv.2108.01265">doi:10.48550/arxiv.2108.01265</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wudcjnwcefhplghpqcfyhivpve">fatcat:wudcjnwcefhplghpqcfyhivpve</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220508115302/https://arxiv.org/pdf/2108.01265.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3e/f1/3ef1be2d60cd21cd8f90645fe9d9da84b9784d96.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.48550/arxiv.2108.01265"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>