「DLP-KDD 2021征文」及上届论文全集，包含深度学习推荐/广告系统、多目标、模型服务等

在DLP-KDD 2021征稿之际，为大家准备了DLP-KDD2020的全部文章和资源列表，内容涵盖了几乎所有深度学习的业界应用前沿，包括深度学习推荐系统应用，多目标优化，Bandit，Learning to rank，模型服务等前沿方向。

DLP-KDD作为学术盛会KDD的下设workshop，由阿里发起，这届workshop由来自阿里巴巴/微软/华为/Roku，以及上海交通大学/犹他大学等工业界/学术界资深同行组成主席团，旨在促进深度学习在广告、推荐、搜索场景下的应用与业界交流，录用文章的工程性，实用性很强，推荐算法工程师同行们阅读。

同时，DLP-KDD 2021即将召开，欢迎大家积极投稿参与（截稿日期2021年5月10日，可根据具体情况适当延期），所有录用论文将会被ACM-DL（https://dl.acm.org/doi/proceedings/10.1145/3326937）或Springer收录收录，详细信息请参照如下征稿文章：

https://zhuanlan.zhihu.com/p/364358132

介绍完DLP-KDD 2021，下面为大家介绍上一届DLP-KDD 2020的收录论文及原文链接：（请点击原文阅读获取全部论文pdf）

(Best Paper Award)COLD: Towards the Next Generation of Pre-Ranking System Zhe Wang, Liqin Zhao, Biye Jiang, Guorui Zhou, Xiaoqiang Zhu and Kun Gai

业界特点非常强的文章，介绍了阿里极高QPS的环境下的深度学习召回/预排序解决方案，强烈推荐。

(Best Paper Runner-Up) Learning-To-Rank with Context-Aware Position DebiasingKeyi Xiao, Xuezhi Cao, Peihao Huang, Sheng Chen, Xiang Zhou, Yunsen Xian

Position Debiasing是业界非常令人困扰的问题，同样是一篇不可多得的已经在美团场景下应用的工业级文章。

(Best Paper Runner-Up)DCAF: A Dynamic Computation Allocation Framework for Online Serving System Biye Jiang, Pengye Zhang, Rihan Chen, Binding Dai, Xinchen Luo, Yin Yang, Guan Wang, Guorui Zhou, Xiaoqiang Zhu and Kun Gai

深度学习环境下的计算资源成为非常紧缺的资源，需要合理进行分配使用，DCAF是阿里巴巴提出的动态计算资源弹性分配框架，同样是一篇业界属性非常强的实用文章。

其他录用文章：

Selling Products by Machine: a User-Sensitive Adversarial Training method for Short Title Generation in Mobile E-CommerceManyi Wang, Tao Zhang, Qijin Chen, Chengfu Huo and Weijun Ren

xDeepInt: a hybrid architecture for modeling the vector-wise and bit-wise feature interactions Yachen Yan and Liubo Li

FLEN: Leveraging Field for Scalable CTR Prediction Wenqiang Chen, Lizhang Zhan, Yuanlong Ci, Minghua Yang, Chen Lin and Dugang Liu

Ranking with Deep Multi-Objective Learning Xuezhi Cao, Sheng Zhu, Biao Tang, Rui Xie, Fuzheng Zhang and Zhongyuan Wang

Categorization of Social Actors in Social Network Analysis (SNA) using Representation Learning via Knowledge-Graph Embeddings and Convolution Operations (RLVECO) Bonaventure Molokwu, Shaon Bhatta Shuvo and Ziad Kobti

Autoencoder Anomaly Detection on Large CAN Bus Data Elena Novikova, Vu Le, Matvey Yutin, Michael Weber and Cory Anderson

Personalized Re-ranking for Improving Diversity in Live Recommender Systems Yichao Wang, Xiangyu Zhang, Zhirong Liu, Zhenhua Dong, Xinhua Feng, Ruiming Tang and Xiuqiang He

Distilled Bandit for Real-time Online Optimization Ziying Liu, Yu Sun, Jianjie Ma, Haiyan Luo, Yujing Wu and Elizabeth Lattanzio

Review Regularized Neural Collaborative Filtering Zhimeng Pan, Wenzheng Tao and Qingyao Ai

Training Deep Learning Recommendation Model with Quantized Collective Communications Jie Yang, Jongsoo Park, Srinivas Sridharan and Ping Tak Peter Tang

Correct Normalization Matters: Understanding the Effect of Normalization On Deep Neural Network Models For Click-Through Rate Prediction Zhiqiang Wang, Qingyun She, Pengtao Zhang and Junlin Zhang

PinText 2: Attentive Bag of Annotations Embedding Jinfeng Zhuang, Jennifer Zhao, Anant Subramanian, Yun Lin, Balaji Krishnapuram and Roelof Zwol

Anomaly detection for sparse data A framework based on PU-Learning and GAN’sAndrew Shields and Ted Scully

Automated Model Selection for Time-Series Anomaly Detection Yuanxiang Ying, Juanyong Duan, Chunlei Wang, Yujing Wang, Congrui Huang and Bixiong Xu

PareCO: Pareto-aware Channel Optimization for Slimmable Neural Networks Ting-Wu Chin, Ari Morcos and Diana Marculescu

DLP-KDD 2021研讨会相关安排

通过上一届论文的介绍，大家可以看到DLP-KDD非常欢迎业界工程师的文章投稿，我们欢迎业界一线的模型及相关基础设施、架构的应用、改进经验。包括但不限于模型改进（Bert，Transformer，多目标学习，LTR，深度学习模型结构，Attention等）、模型服务、线上推荐流程等方向，欢迎大家投稿，并参加线下及线上的业界讨论交流。

请点击原文阅读 链接获取，全部论文下载链接 。（复制链接内容直接发送到微信对话框链接即可直接打开）