Sunnyvale, California, United States
Contact Info
2K followers
500+ connections
About
Activity
-
Today I hang up my IBM badge. It's bittersweet. I don't view my departure as one in which I'm leaving the company, but rather one in which I'm going…
Today I hang up my IBM badge. It's bittersweet. I don't view my departure as one in which I'm leaving the company, but rather one in which I'm going…
Liked by Dawei Yin
-
I am honored to have been selected as a recipient of the prestigious National Science Foundation (NSF) CAREER Award!!! Thanks for the generous…
I am honored to have been selected as a recipient of the prestigious National Science Foundation (NSF) CAREER Award!!! Thanks for the generous…
Liked by Dawei Yin
-
Honored to be conferred as an ACM Distinguished Member, for contributions to algorithms on large-scale data processing. My heartiest thanks to my…
Honored to be conferred as an ACM Distinguished Member, for contributions to algorithms on large-scale data processing. My heartiest thanks to my…
Liked by Dawei Yin
Experience & Education
Publications
-
Recommendation in Academia: A joint multi-relational model
ASONAM
-
Convex Collective Matrix Factorizatoin
Proceedings of the 16th International Conference on Artificial Intelligence and Statistics (AISTATS-13)
In many applications, multiple interlinked sources of data are available and they cannot be represented by a single adjacency matrix, to which large scale factorization method could be applied. Collective matrix factorization is a simple yet powerful approach to jointly factorize multiple matrices, each of which represents a relation between two entity types. Existing algorithms to estimate parameters of collective matrix factorization models are based on non-convex formulations of the problem;…
In many applications, multiple interlinked sources of data are available and they cannot be represented by a single adjacency matrix, to which large scale factorization method could be applied. Collective matrix factorization is a simple yet powerful approach to jointly factorize multiple matrices, each of which represents a relation between two entity types. Existing algorithms to estimate parameters of collective matrix factorization models are based on non-convex formulations of the problem; in this paper, a convex formulation of this approach is proposed. This enables the derivation of large scale algorithms to estimate the parameters, including an iterative eigenvalue thresholding algorithm. Numerical experiments illustrate the benefits of this new approach.
Other authorsSee publication -
Connecting Comments and Tags: Improved Modeling of Social Tagging Systems
Proceedings of the 6th International ACM Conference on Web Search and Data Mining 2013 (WSDM-13)
-
Exploiting Session-like Behaviors in Tag Prediction [Poster]
In the proceedings of the 20th international conference on World Wide Web (WWW 2011)
Dawei Yin is the first author.
-
Causal Inference via Sparse Additive Models with Application to Online Advertising
Accepted by AAAI 2015.
Advertising effectiveness measurement is a fundamental problem in online advertising. Various causal inference methods have been employed to measure the causal effects of binary ad treatments. However, existing methods mainly focus on linear logistic regression for univariate and binary treatments and are not well suited for complex ad treatments which are more realistic and in great demand. In this paper we propose a novel two-stage causal inference framework for assessing the impact of…
Advertising effectiveness measurement is a fundamental problem in online advertising. Various causal inference methods have been employed to measure the causal effects of binary ad treatments. However, existing methods mainly focus on linear logistic regression for univariate and binary treatments and are not well suited for complex ad treatments which are more realistic and in great demand. In this paper we propose a novel two-stage causal inference framework for assessing the impact of complex ad treatments. In the first stage, we estimate the propensity parameter via a sparse additive model; in the second stage, a propensity-adjusted regression model is applied for measuring the treatment effect. Our framework enables analysis on multi-dimensional ad treatments, where each dimension could be discrete or continuous. The enforced sparse additive model is well suited for high-dimensional and nonlinear advertising data. Furthermore, we prove that our two-stage approach is able to provide an unbiased estimation of the ad effectiveness under regularity conditions. To demonstrate the efficacy of our approach, we apply it to an real online advertising campaign to evaluate the impact of three ad treatments: ad frequency, ad channel, and ad size. We show that the ad frequency usually has a treatment effect cap when ads are showing on mobile device. In addition, the strategies for choosing best ad size are completely different for mobile ads and online ads.
Other authors
Patents
Languages
-
Chinese
-
More activity by Dawei
-
Thrilled to start 2024 with an incredibly exciting new adventure! I am opening in Haifa, Israel, an AI/IR Research Center for the Technology…
Thrilled to start 2024 with an incredibly exciting new adventure! I am opening in Haifa, Israel, an AI/IR Research Center for the Technology…
Liked by Dawei Yin
-
Delighted and honored to be recognized as AAAI Fellow. Grateful for amazing students, collaborators and mentors over the years.
Delighted and honored to be recognized as AAAI Fellow. Grateful for amazing students, collaborators and mentors over the years.
Liked by Dawei Yin
-
🚀 Join Our Team to Revolutionize Monetization Solutions! Are you passionate about crafting cutting-edge, world-class monetization solutions? Do you…
🚀 Join Our Team to Revolutionize Monetization Solutions! Are you passionate about crafting cutting-edge, world-class monetization solutions? Do you…
Liked by Dawei Yin
-
Hire ML Engineers at Meta Hey folks, we at Meta are hiring ML engineers to define and solve ambiguous problem, which can (1) bring most enjoyable…
Hire ML Engineers at Meta Hey folks, we at Meta are hiring ML engineers to define and solve ambiguous problem, which can (1) bring most enjoyable…
Liked by Dawei Yin
-
Astara is now live on App Store! Wondering if today is the day to make bold moves in options trading? Ask your personal AI astrologer for guidance…
Astara is now live on App Store! Wondering if today is the day to make bold moves in options trading? Ask your personal AI astrologer for guidance…
Liked by Dawei Yin
-
The 17th edition of AdKDD is a wrap! Thank you to our keynote speakers Ashvin Kannan, Michael Ostrovsky and Shobha Diwakar Thanks also to our…
The 17th edition of AdKDD is a wrap! Thank you to our keynote speakers Ashvin Kannan, Michael Ostrovsky and Shobha Diwakar Thanks also to our…
Liked by Dawei Yin
-
Thrilled to announce the keynote speakers for AdKDD'23 (www.adkdd.org) which is at its 16th edition! We are honored to host Ashvin Kannan (LinkedIn),…
Thrilled to announce the keynote speakers for AdKDD'23 (www.adkdd.org) which is at its 16th edition! We are honored to host Ashvin Kannan (LinkedIn),…
Liked by Dawei Yin
-
Please check out the 2-min intro video of our recent KDD paper on path-specific fairness in recommender systems!
Please check out the 2-min intro video of our recent KDD paper on path-specific fairness in recommender systems!
Liked by Dawei Yin
-
I‘m super excited to become an applied research intern @ Baidu, Inc. from Jun 2023, under the leadership of Dawei Yin! #research #intern…
I‘m super excited to become an applied research intern @ Baidu, Inc. from Jun 2023, under the leadership of Dawei Yin! #research #intern…
Liked by Dawei Yin
-
🎉 Exciting news! I'm thrilled to share that I’ve been awarded the prestigious National Science Foundation (NSF) CAREER Award! 🏆 I'm incredibly…
🎉 Exciting news! I'm thrilled to share that I’ve been awarded the prestigious National Science Foundation (NSF) CAREER Award! 🏆 I'm incredibly…
Liked by Dawei Yin
-
I'm organizing a workshop on Machine Learning for Streaming Media on Sunday (April 30th) at the WebConf 2023 along with my colleagues - Sudarshan…
I'm organizing a workshop on Machine Learning for Streaming Media on Sunday (April 30th) at the WebConf 2023 along with my colleagues - Sudarshan…
Liked by Dawei Yin
-
After an incredible 5-year journey at Meta, I am excited to announce that I am joining Flip as the Head of AI and Data Science. Flip is a startup…
After an incredible 5-year journey at Meta, I am excited to announce that I am joining Flip as the Head of AI and Data Science. Flip is a startup…
Liked by Dawei Yin
People also viewed
-
Daniel Chen
Connect -
Xiaolin Shi
Connect -
Brian Mun
Connect -
Liangjie Hong
Connect -
cheng zhicong
senior researcher - ranking at Baidu, Inc.
Connect -
Lilian Weng
Connect -
Juntao Liu
Researcher at 709th Research Institute,China Shipbuilding Industry Corporation
Connect -
Haixun Wang
Connect -
Jing Chen
Robotics and Algorithms | System Architect | Intelligent Driving Industry | R&D Management.
Connect -
Xubin Ren
Data Science Ph.D. Student @ HKU
Connect
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Dawei Yin
-
Dawei Y.
MSCS@Columbia University | BU Alum
-
Dawei Yin
Marketing Technical Principal at ThoughtWorks
-
Dawei Yin 殷大伟
-
Dawei Yin
146 others named Dawei Yin are on LinkedIn
See others named Dawei Yin