1 code implementation • 31 May 2023 • Xue Xia, Pong Eksombatchai, Nikil Pancha, Dhruvil Deven Badani, Po-Wei Wang, Neng Gu, Saurabh Vishwas Joshi, Nazanin Farahpour, Zhiyuan Zhang, Andrew Zhai
This paper (1) presents Pinterest's ranking architecture for Homefeed, our personalized recommendation product and the largest engagement surface; (2) proposes TransAct, a sequential model that extracts users' short-term preferences from their realtime activities; (3) describes our hybrid approach to ranking, which combines end-to-end sequential modeling via TransAct with batch-generated user embeddings.
no code implementations • 18 Sep 2022 • Jiajing Xu, Andrew Zhai, Charles Rosenberg
In this work, we present our journey to revolutionize the personalized recommendation engine through end-to-end learning from raw user actions.
no code implementations • 24 May 2022 • Paul Baltescu, Haoyu Chen, Nikil Pancha, Andrew Zhai, Jure Leskovec, Charles Rosenberg
Learned embeddings for products are an important building block for web-scale e-commerce recommendation systems.
no code implementations • 21 May 2022 • Saket Gurukar, Nikil Pancha, Andrew Zhai, Eric Kim, Samson Hu, Srinivasan Parthasarathy, Charles Rosenberg, Jure Leskovec
MultiBiSage can capture the graph structure of multiple bipartite graphs to learn high-quality pin embeddings.
no code implementations • 9 May 2022 • Nikil Pancha, Andrew Zhai, Jure Leskovec, Charles Rosenberg
Sequential models have become increasingly popular in powering personalized recommendation systems over the past several years.
no code implementations • 12 Aug 2021 • Josh Beal, Hao-Yu Wu, Dong Huk Park, Andrew Zhai, Dmitry Kislyuk
Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems has been relatively unexplored.
Ranked #26 on Image Classification on ObjectNet (using extra training data)
no code implementations • 17 Dec 2020 • Josh Beal, Eric Kim, Eric Tzeng, Dong Huk Park, Andrew Zhai, Dmitry Kislyuk
The Vision Transformer was the first major attempt to apply a pure transformer model directly to images as input, demonstrating that as compared to convolutional networks, transformer-based architectures can achieve competitive results on benchmark classification tasks.
1 code implementation • 18 Jun 2020 • Eileen Li, Eric Kim, Andrew Zhai, Josh Beal, Kunlong Gu
In this paper, we will describe how we bootstrapped the Complete The Look (CTL) system at Pinterest.
no code implementations • 18 Jun 2020 • Raymond Shiau, Hao-Yu Wu, Eric Kim, Yue Li Du, Anqi Guo, Zhiyuan Zhang, Eileen Li, Kunlong Gu, Charles Rosenberg, Andrew Zhai
As online content becomes ever more visual, the demand for searching by visual queries grows correspondingly stronger.
no code implementations • 5 Aug 2019 • Andrew Zhai, Hao-Yu Wu, Eric Tzeng, Dong Huk Park, Charles Rosenberg
The solution we present not only allows us to train for multiple application objectives in a single deep neural network architecture, but takes advantage of correlated information in the combination of all training data from each application to generate a unified embedding that outperforms all specialized embeddings previously deployed for each product.
2 code implementations • 30 Nov 2018 • Andrew Zhai, Hao-Yu Wu
Deep metric learning aims to learn a function mapping image pixels to embedding feature vectors that model the similarity between images.
Ranked #3 on Image Retrieval on CARS196
no code implementations • 15 Feb 2017 • Andrew Zhai, Dmitry Kislyuk, Yushi Jing, Michael Feng, Eric Tzeng, Jeff Donahue, Yue Li Du, Trevor Darrell
Over the past three years Pinterest has experimented with several visual search and recommendation services, including Related Pins (2014), Similar Looks (2015), Flashlight (2016) and Lens (2017).
no code implementations • 28 May 2015 • Yushi Jing, David Liu, Dmitry Kislyuk, Andrew Zhai, Jiajing Xu, Jeff Donahue, Sarah Tavel
We demonstrate that, with the availability of distributed computation platforms such as Amazon Web Services and open-source tools, it is possible for a small engineering team to build, launch and maintain a cost-effective, large-scale visual search system with widely available tools.