Deep Learning papers for industrial Search, Recommendation and Advertisement论文集收录了深度学习在行业搜索,推荐和广告上的应用论文。内容包括嵌入,匹配,排名(点击率预测,CVR预测),职位排名,迁移和强化学习。
Zhang Yang,Feng Fuli, Wang Chenxu,He Xiangnan,Wang Meng, Li Yan,Zhang Yongdong
SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Re..., pp.1479-1488, (2020)
We study the model retraining mechanism for recommender systems, a topic of high practical values but has been relatively little explored in the research community
Cited by4BibtexViews191DOI
0
0
Lixin Zou, Long Xia, Yulong Gu, Xiangyu Zhao,Weidong Liu, Jimmy Xiangji Huang, Dawei Yin
SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Re..., pp.749-758, (2020)
We study collaborative filtering in an interactive setting, in which the recommender agents iterate between making recommendations and updating the user profile based on the interactive feedback
Cited by3BibtexViews28DOI
0
0
KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Virtual Event..., pp.2942-2951, (2020)
Recommender systems start a new phase owing to the rapid development of deep learning
Cited by2BibtexViews908DOI
0
0
KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Virtual Event..., pp.2900-2908, (2020)
We provided examples of successful modeling techniques as well as pitfalls, and hope that they provide a useful case study for those interested in building recommendation systems over private corpora
Cited by1BibtexViews37DOI
0
0
WSDM '20: The Thirteenth ACM International Conference on Web Search and Data Mining Houston ..., pp.331-339, (2020)
We propose a novel dual transfer learning based model that significantly improves recommendation performance across different domains
Cited by1BibtexViews12DOI
0
0
KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Virtual Event..., pp.2553-2561, (2020)
We evaluated embedding-based retrieval on verticals for Facebook Search with significant metrics gains observed in online A/B experiments
Cited by0BibtexViews123DOI
0
0
KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Virtual Event..., pp.2952-2960, (2020)
We describe our journey in tackling the problem of diversity for Airbnb search, starting from heuristic based approaches and concluding with a novel deep learning solution that produces an embedding of the entire query context by leveraging Recurrent Neural Networks
Cited by0BibtexViews86DOI
0
0
Li Xiang, Wang Chao, Tan Jiwei, Zeng Xiaoyi, Ou Dan, Zheng Bo
WWW '20: The Web Conference 2020 Taipei Taiwan April, 2020, pp.827-836, (2020)
We propose a multimodal attention fusion network
Cited by0BibtexViews2DOI
0
0
KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Virtual Event..., pp.3319-3327, (2020)
We propose a two-level deep reinforcement learning framework Rec/Ads Mixed display with novel Deep Q-network architectures for the mixed display of recommendation and advertising in online recommender systems
Cited by0BibtexViews50DOI
0
0
Yu Gong, Ziwen Jiang, Yufei Feng, Binbin Hu, Kaiqi Zhao,Qingwen Liu,Wenwu Ou
CIKM '20: The 29th ACM International Conference on Information and Knowledge Management Virt..., pp.2477-2484, (2020)
We propose Heterogeneous User Behavior Sequence Modeling and Context-aware Reranking with Behavior Attention Networks to capture user’s diverse interests and adjust recommendation results
Cited by0BibtexViews11DOI
0
0
Yiding Liu, Yulong Gu, Zhuoye Ding, Junchao Gao, Ziyi Guo,Yongjun Bao, Weipeng Yan
CIKM '20: The 29th ACM International Conference on Information and Knowledge Management Virt..., pp.2621-2628, (2020)
We propose an effective decoupled Graph Convolutional Network for the task of inferring substitutable and complementary items
Cited by0BibtexViews2DOI
0
0
Yulong Gu,Zhuoye Ding, Shuaiqiang Wang,Lixin Zou, Yiding Liu,Dawei Yin
CIKM '20: The 29th ACM International Conference on Information and Knowledge Management Virt..., pp.2493-2500, (2020)
Multi-gate Mixture-of-Experts to jointly optimize multi-objectives in e-commerce, and uses the Bias Deep Neural Networks to reduce the select bias in implicit feedback
Cited by0BibtexViews95DOI
0
0
Wentao Ouyang, Xiuwu Zhang, Lei Zhao, Jinmei Luo, Yu Zhang, Heng Zou, Zhaojie Liu, Yanlong Du
CIKM '20: The 29th ACM International Conference on Information and Knowledge Management Virt..., pp.2669-2676, (2020)
We address the cross-domain Click-through rate prediction problem for online advertising
Cited by0BibtexViews8DOI
0
0
Chen Xu, Quan Li, Junfeng Ge,Jinyang Gao,Xiaoyong Yang,Changhua Pei,Fei Sun, Jian Wu, Hanxiao Sun,Wenwu Ou
KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Virtual Event..., pp.2590-2598, (2020)
We identify the privileged features existing at Taobao recommendations, i.e., the interacted features for click-through rate at coarsegrained ranking and the post-event features for conversion rate at fine-grained ranking
Cited by0BibtexViews133DOI
0
0
Tan Yu,Yi Yang,Yi Li, Xiaodong Chen, Mingming Sun,Ping Li
KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Virtual Event..., pp.2474-2482, (2020)
We evaluate the proposed combo-attention network in Baidu dynamic video advertising platform
Cited by0BibtexViews271DOI
0
0
SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Re..., pp.1469-1478, (2020)
We have shown that it is possible to learn universal user representations by modeling only unsupervised user sequential behaviors; and it is possible to adapt the learned representations for a variety of downstream tasks
Cited by0BibtexViews180DOI
0
0
ICML, pp.11650-11659, (2020)
Little attention has been paid to the training-testing discrepancy where the retrieval performance deterioration caused by beam search in testing is ignored in training
Cited by0BibtexViews40DOI
0
0
Xu Weinan, He Hengxu,Tan Minshi, Li Yunming, Lang Jun, Guo Dongbai
SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Re..., pp.1905-1908, (2020)
Considering the deployment in recommendation scenarios, a simplified Deep Interest with Hierarchical Attention Network has been applied to three public datasets, and has achieved significant uplift of AUC around 12% to 21% over Deep Interest Network and slight uplift of AUC aroun...
Cited by0BibtexViews13DOI
0
0
Feng Yufei, Hu Binbin,Lv Fuyu, Liu Qingwen,Zhang Zhiqiang,Ou Wenwu
SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Re..., pp.2231-2240, (2020)
We propose a new framework named Adaptive Target-Behavior Relational Graph network to effectively capture structural relations of target user-item pairs over knowledge graph
Cited by0BibtexViews42DOI
0
0
We focus on embedding learning for Attributed MHEN, where different types of nodes might be linked with multiple different types of edges, and each node is associated with a set of different attributes
Cited by64BibtexViews461DOI
1
0