With the popularity of various forms of E-commerce, web advertising has become one prominent channel that businesses use to reach out to the customers. It leverages the Internet to promote products and services to audiences, which also has been an important revenue source of many Internet companies such as online social media platforms and search engines.
AI techniques have been extensively used in the pipeline of a web advertising system, such as retrieval, ranking and bidding. Despite the remarkable progress, there are still many unsolved and emerging issues about applying the state-of-the-art AI techniques to Web Advertising, such as the “cold-start” problem; trade-off between online AI systems serving accuracy and efficiency; data privacy protection and big data management.
This workshop is targeted on the above and other relevant issues, aiming to create a platform for people from academia and industry to communicate their insights and recent results.
Time (EST) | Speaker | Title |
---|---|---|
8:30-8:35 | Opening remark | |
8:35-9:35 | Jiliang Tang (Michigan State University) | Toward Automated Deep Recommender Systems |
9:35-10:35 | Musen Wen (Walmart Ads) | Computational Advertising in e-Commerce: an Industry Review and New Challenge |
10:35-11:00 | Break | Break |
11:00-11:15 | Zhimeng Jiang (Texas A&M University); Kaixiong Zhou (Rice University); Mi Zhang (Samsung Research America); Rui Chen (Samsung Research America); Xia Hu (Rice University); Soo-Hyun Choi (Samsung Electronics) | Adaptive Risk-Aware Bidding with Budget Constraint in Display Advertising paper supplementary |
11:15-11:30 | Bo Luo (OPPO Research Institute); Dan Meng (OPPO Research Institute); Fu Zhihui (OPPO Research); Jun Wang (OPPO Research Institute); Chao Kong (Anhui Polytechnic University); Qiuying Peng (OPPO Research Institute); Yue Qi (OPPO Research Institute | PMCE: Personalized Mutual Cloud-end Federated Graph Learning for Recommendation paper |
11:30-11:45 | Olivier Jeunen (Amazon); Lampros Stavrogiannis (Amazon); Amin Sayedi (Amazon); Ben Allison (Amazon) | A Probabilistic Framework to Learn Auction Mechanisms via Gradient Descent paper |
11:45-12:00 | Fynn Oldenburg (Nova School of Business and Economics); Qiwei Han (Nova School of Business and Economics); Maximilian Kaiser (Grips) | Forecasting Budget-Dependent CPCs: Learn From Your Competitors paper |
12:00-12:15 | Jiahua Chen (University of Illinois at Chicago); Andrei Simion (Walmart); Yanbing Xue (Walmart); Musen Wen (Walmart) | A Tree-Based Extreme Multi-label Learning Method for E-Commerce Sponsor Matching |
12:15-14:00 | Lunch Break | Lunch Break |
14:00-15:00 | Chen Luo (Amazon) | Towards Scalable, Unbiased, and Interactive Product Search |
15:00-15:15 | Yanbing Xue (University of Pittsburgh); Bo Liu (JD.com); Weizhi Du (University of Michigan); Jayanth Korlimarla (Walmart eCommerce); Musen Wen (Walmart eCommerce) | Practical Lessons on Optimizing Sponsored Products in eCommerce paper |
15:15-15:30 | Yunqi Li (Rutgers University); Michiharu Yamashita (The Pennsylvania State University); Hanxiong Chen (Rutgers University); Dongwon Lee (Penn State University); Yongfeng Zhang (Rutgers University) | Fairness in Job Recommendation under Quantity Constraints paper |
15:30-16:00 | Break | Break |
16:00-17:00 | Yongfeng Zhang (Rutgers University) | Towards Trustworthy Recommender Systems: From Shallow Models to Deep Models to Large Models |
17:00-17:15 | Ragja Palakkadavath (Deakin University); Sarath Sivaprasad (TCS Research); Shirish Karande (TCS Research); Niranjan Pedanekar (TCS Research) | I Know Therefore I Score: Label-Free Crafting of Scoring Functions using Constraints Based on Domain Expertise paper |
17:15-17:30 | Sachin Narayan Nagargoje (Indian Institute of Science) | Cooperative Approach to Increase Recall in Online Shopping Domain to Match Structured Data with Unstructured Data paper |
17:30-17:45 | Fanglan Zheng (Everbright Technology) | Causal Inference Based Single-branch Ensemble Trees For Uplift Modeling paper |
17:45-17:50 | Closing remark |
Towards Scalable, Unbiased, and Interactive Product Search
Product search engines like Amazon Search provide online shopping services for billions of people worldwide. Our goal at Amazon Search is to provide a fast, unbiased, and enjoyable shopping experience for our customers. In this talk, I will share our recent research achievements in making product search scalable, unbiased, and interactive. I will introduce (1) how to scaling up search by using randomized algorithms, (2) how to do unbiased online learning to rank, and (2) how to use session information for more informative search.
Toward Automated Deep Recommender Systems
Deep learning has injected new life into recommender systems and deep recommender systems (DRS) have achieved very promising performance in various recommendation scenarios. Compared to traditional recommendation methods, DRSs often have complicated architectures in order to embed complex representations of users/items and simulate nonlinear user-item interaction pattern. To build a deep model for a given recommendation task, we often need to design its architecture in a hand-crafted manner. However, the design space for these layers can be huge. Therefore, automatically designing these layers is highly desired. In this talk, I will discuss how to automatically determine the embedding dimension and discover the optimal loss function for DRSs.
Computational Advertising in e-Commerce: an Industry Review and New Challenge
Online advertising, both displayed ads and sponsored search, have been powering the internet business in the past two decades. In recent years, advertising has become the new fly-wheel for eCommerce platforms. It provides an effective marketing channel for advertisers, generating sizable revenue for the platform and providing an enriched experience for shoppers. This talk will review the commonality and differences in the marketplace platforms. We will also discuss the challenge and open problems from the view of modern computational advertising and future directions.
Towards Trustworthy Recommender Systems: From Shallow Models to Deep Models to Large Models
As the bridge between humans and AI, recommender system is at the frontier of Human-centered AI research. However, inappropriate use or development of recommendation techniques may bring negative effects to humans and the society at large, such as user distrust due to the non-transparency of the recommendation mechanism, unfairness of the recommendation algorithm, user uncontrollability of the recommendation system, as well as user privacy risks due to the extensive use of users’ private data for personalization. In this talk, we will discuss how to build trustworthy recommender systems along the progress that recommendation algorithms advance from shallow models to deep models to large models, including but not limited to the unique role of recommender system research in the AI community as a representative Subjective AI task, the relationship between Subjective AI and trustworthy computing, as well as typical recommendation methods on different perspectives of trustworthy computing, such as causal and counterfactual reasoning, neural-symbolic modeling, natural language explanations, federated learning, user controllable recommendation, echo chamber mitigation, personalized prompt learning, and beyond.
Chen Luo is a Senior Applied Scientist and Tech Lead at Amazon Search, leading a team of scientists and engineers in query understanding and its applications in matching, ranking, and advertising. His research focuses on scalable machine learning for information retrieval and recommender systems. He received his Ph.D. from Rice University and has published in ML and IR conferences and journals such as WWW, KDD, SIGIR, AAAI, and JMLR. He regularly serves as SPC or PC for NeurIPS, ICML, KDD, AAAI, and WWW.
Dr. Jiliang Tang is a University Foundation Professor in the computer science and engineering department at Michigan State University. He was an Associate Professor (2021-2022) and an Assistant Professor (2016-2021) in the same department.. Before that, he was a research scientist in Yahoo Research. He got his Ph.D. from Arizona State University in 2015 and MS and BE from Beijing Institute of Technology in 2010 and 2008, respectively. His research interests include graph machine learning, trustworthy AI, and their applications in Education and Biology. He authored the first comprehensive book “deep learning on graphs” with Cambridge University Press and developed various well-received open-sourced tools including scikit-feature for feature selection, DeepRobust for trustworthy AI and DANC for single-cell analysis. He was the recipient of various career awards (2022 IAPR J. K. AGGARWAL, 2022 SIAM SDM, 2021 IEEE ICDM, 2021 IEEE Big Data Security, 2020 ACM SIGKDD, 2019 NSF), numerous industrial faculty awards and 8 best paper awards (or runner-ups) including WSDM2018 and KDD2016. He serves as conference organizers (e.g., KDD, SIGIR, WSDM and SDM) and journal editors (e.g., TKDD and TKDE). He has published his research in highly ranked journals and top conference proceedings, which have 25,000 citations with h-index 77 and extensive media coverage.
Musen Wen is a Senior Machine Learning Engineering and Data Science Manager at Walmart eCommerce, working on computational advertising. Prior to this, he has been working as research and applied scientist at Apple, eBay, Yahoo and Microsoft. His work has been largely evolving building large-scale machine learning and deep learning systems to solve industrial problems such as search and sponsored search ranking, query understanding, advertising audience targeting, eCommerce product recommendation, semi-supervised learning and active learning, etc.. He has co-authored top conferences paper including ACL, KDD, WSDM, RecSys, etc.. He got his PhD degree in Statistical Machine Learning from the University of California and his research interests include machine learning and deep learning etc..
Yongfeng Zhang is an Assistant Professor in the Department of Computer Science at Rutgers University. His research interest is in Machine Learning, Machine Reasoning, Information Retrieval, Recommender Systems, Explainable AI, and Fairness in AI. His research works appear in top-tier conferences in related areas such as SIGIR, WWW, RecSys, ACL, NAACL, CIKM, WSDM, AAAI, IJCAI, TOIS, etc. He serves as associate editor for ACM Transactions on Information Systems (TOIS), ACM Transactions on Recommender Systems (TORS), and Frontiers in Big Data. He is a Siebel Scholar of the class 2015 and an NSF career awardee in 2021.
Topics of interest include, but are not limited to, the following:
Submissions should follow the AAAI-23 template. There is no page limit for the paper submission. Paper submission will be reviewed by domain experts. Paper submission link: https://cmt3.research.microsoft.com/AI4WebAds2023
Accepted papers will be posted on the workshop webpage. We welcome submissions of unpublished papers, including those that are submitted/accepted to other venues if that other venue allows so.
Workshop paper submission deadline: Friday, November 4, 2022
Workshop paper acceptance notification: Friday, November 18, 2022Saturday, November 26, 2022
Workshops are scheduled to run: TBD
Staff Data Scientist
Walmart Ads
Research Scientist
Meta Ads
Engineering Leader
Twitter Ads