Jun Yu
Jun Yu has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Neil Shah
Snap Inc., Bellevue, WA, USA
3 shared publications - Yozen Liu
Snap Inc., Santa Monica, CA, USA
3 shared publications - Ganesh Venkataraman
Snap, Palo Alto, CA, USA
2 shared publications - Jiahui Shi
Snap, Palo Alto, CA, USA
2 shared publications - Peicheng Yu
Department of Engineering Physics, Tsinghua University, Beijing 100084, PR China
2 shared publications - Shubham Vij
Snap Inc., Bellevue, WA, USA
2 shared publications
Latest Publications
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5225-5236
GiGL: Large-Scale Graph Neural Networks at Snapchat
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5225-5236
Open AccessGiGL: Large-Scale Graph Neural Networks at Snapchat
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2930-2934
Improving Embedding-Based Retrieval in Friend Recommendation with ANN Query Expansion
Embedding-based retrieval in graph-based recommendation has shown great improvements over traditional graph walk retrieval methods, and has been adopted in large-scale industry applications such as friend recommendations [16]. However, it is not without its challenges: retraining graph embeddings frequently due to changing data is slow and costly, and producing high recall of approximate nearest neighbor search (ANN) on such embeddings is challenging due to the power law distribution of the indexed users. In this work, we address theses issues by introducing a simple query expansion method in ANN, called FriendSeedSelection, where for each node query, we construct a set of 1-hop embeddings and run ANN search. We highlight our approach does not require any model-level tuning, and is inferred from the data at test-time. This design choice effectively enables our recommendation system to adapt to the changing graph distribution without frequent heavy model retraining. We also discuss how we design our system to efficiently construct such queries online to support 10k+ QPS. For friend recommendation, our method shows improvements of recall, and 11% relative friend reciprocated communication metric gains, now serving over 800 million monthly active users at Snapchat.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2930-2934
Open AccessImproving Embedding-Based Retrieval in Friend Recommendation with ANN Query Expansion
Embedding-based retrieval in graph-based recommendation has shown great improvements over traditional graph walk retrieval methods, and has been adopted in large-scale industry applications such as friend recommendations [16]. However, it is not without its challenges: retraining graph embeddings frequently due to changing data is slow and costly, and producing high recall of approximate nearest neighbor search (ANN) on such embeddings is challenging due to the power law distribution of the indexed users. In this work, we address theses issues by introducing a simple query expansion method in ANN, called FriendSeedSelection, where for each node query, we construct a set of 1-hop embeddings and run ANN search. We highlight our approach does not require any model-level tuning, and is inferred from the data at test-time. This design choice effectively enables our recommendation system to adapt to the changing graph distribution without frequent heavy model retraining. We also discuss how we design our system to efficiently construct such queries online to support 10k+ QPS. For friend recommendation, our method shows improvements of recall, and 11% relative friend reciprocated communication metric gains, now serving over 800 million monthly active users at Snapchat.
- Open Access
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 1188-1189
Lessons Learnt from Building Friend Recommendation Systems
Friend recommendation systems in online social networks such as Snapchat help users find friends and build meaningful connections, leading to heightened user engagement and retention. While friend recommendation systems follow the classical recommendation system paradigm that consists of retrieval and ranking, they pose distinctive challenges different from item recommendation systems (e.g. Youtube videos, Amazon products, Netflix movies), and require special considerations in building one. In this paper, we elucidate the unique challenges encountered and share invaluable insights from developing the friend recommendation system for hundreds of millions of users on Snapchat.
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 1188-1189
Open AccessLessons Learnt from Building Friend Recommendation Systems
Friend recommendation systems in online social networks such as Snapchat help users find friends and build meaningful connections, leading to heightened user engagement and retention. While friend recommendation systems follow the classical recommendation system paradigm that consists of retrieval and ranking, they pose distinctive challenges different from item recommendation systems (e.g. Youtube videos, Amazon products, Netflix movies), and require special considerations in building one. In this paper, we elucidate the unique challenges encountered and share invaluable insights from developing the friend recommendation system for hundreds of millions of users on Snapchat.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 3330-3334
Embedding Based Retrieval in Friend Recommendation
Friend recommendation systems in online social and professional networks such as Snapchat helps users find friends and build connections, leading to better user engagement and retention. Traditional friend recommendation systems take advantage of the principle of locality and use graph traversal to retrieve friend candidates, e.g. Friends-of-Friends (FoF). While this approach has been adopted and shown efficacy in companies with large online networks such as Linkedin and Facebook, it suffers several challenges: (i) discrete graph traversal offers limited reach in cold-start settings, (ii) it is expensive and infeasible in realtime settings beyond 1 or 2 hop requests owing to latency constraints, and (iii) it cannot well-capture the complexity of graph topology or connection strengths, forcing one to resort to other mechanisms to rank and find top-K candidates. In this paper, we proposed a new Embedding Based Retrieval (EBR) system for retrieving friend candidates, which complements the traditional FoF retrieval by retrieving candidates beyond 2-hop, and providing a natural way to rank FoF candidates. Through online A/B test, we observe statistically significant improvements in the number of friendships made with EBR as an additional retrieval source in both low- and high-density network markets. Our contributions in this work include deploying a novel retrieval system to a large-scale friend recommendation system at Snapchat, generating embeddings for billions of users using Graph Neural Networks, and building EBR infrastructure in production to support Snapchat scale.
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 3330-3334
Open AccessEmbedding Based Retrieval in Friend Recommendation
Friend recommendation systems in online social and professional networks such as Snapchat helps users find friends and build connections, leading to better user engagement and retention. Traditional friend recommendation systems take advantage of the principle of locality and use graph traversal to retrieve friend candidates, e.g. Friends-of-Friends (FoF). While this approach has been adopted and shown efficacy in companies with large online networks such as Linkedin and Facebook, it suffers several challenges: (i) discrete graph traversal offers limited reach in cold-start settings, (ii) it is expensive and infeasible in realtime settings beyond 1 or 2 hop requests owing to latency constraints, and (iii) it cannot well-capture the complexity of graph topology or connection strengths, forcing one to resort to other mechanisms to rank and find top-K candidates. In this paper, we proposed a new Embedding Based Retrieval (EBR) system for retrieving friend candidates, which complements the traditional FoF retrieval by retrieving candidates beyond 2-hop, and providing a natural way to rank FoF candidates. Through online A/B test, we observe statistically significant improvements in the number of friendships made with EBR as an additional retrieval source in both low- and high-density network markets. Our contributions in this work include deploying a novel retrieval system to a large-scale friend recommendation system at Snapchat, generating embeddings for billions of users using Graph Neural Networks, and building EBR infrastructure in production to support Snapchat scale.