Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- short-paperJuly 2024
Improving Embedding-Based Retrieval in Friend Recommendation with ANN Query Expansion
- Pau Perng-Hwa Kung,
- Zihao Fan,
- Tong Zhao,
- Yozen Liu,
- Zhixin Lai,
- Jiahui Shi,
- Yan Wu,
- Jun Yu,
- Neil Shah,
- Ganesh Venkataraman
SIGIR '24: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information RetrievalJuly 2024, Pages 2930–2934https://doi.org/10.1145/3626772.3661367Embedding-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 ...
- short-paperJuly 2024
General-Purpose User Modeling with Behavioral Logs: A Snapchat Case Study
- Qixiang Fang,
- Zhihan Zhou,
- Francesco Barbieri,
- Yozen Liu,
- Leonardo Neves,
- Dong Nguyen,
- Daniel Oberski,
- Maarten Bos,
- Ron Dotsch
SIGIR '24: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information RetrievalJuly 2024, Pages 2431–2436https://doi.org/10.1145/3626772.3657908Learning general-purpose user representations based on user behavioral logs is an increasingly popular user modeling approach. It benefits from easily available, privacy-friendly yet expressive data, and does not require extensive re-tuning of the ...
- research-articleFebruary 2024
Unpacking the exploration–exploitation tradeoff on Snapchat: The relationships between users’ exploration–exploitation interests and server log data
Computers in Human Behavior (COHB), Volume 150, Issue CJan 2024https://doi.org/10.1016/j.chb.2023.108014AbstractSocial media users continuously decide between looking for familiar content and exploring novel content. Although prior research has extensively studied the trade-off between exploration and exploitation (E/E), little is known about how it ...
Highlights- Snapchat users’ behavioral signals were mainly associated with exploration interests rather than exploitation interests.
- Exploration was positively associated with spending more time and having more impressions on Snapchat.
- ...
- research-articleAugust 2023
CARL-G: Clustering-Accelerated Representation Learning on Graphs
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2023, Pages 2036–2048https://doi.org/10.1145/3580305.3599268Self-supervised learning on graphs has made large strides in achieving great performance in various downstream tasks. However, many state-of-the-art methods suffer from a number of impediments, which prevent them from realizing their full potential. For ...
- research-articleJuly 2023
Linkless link prediction via relational distillation
ICML'23: Proceedings of the 40th International Conference on Machine LearningJuly 2023, Article No.: 482, Pages 12012–12033Graph Neural Networks (GNNs) have shown exceptional performance in the task of link prediction. Despite their effectiveness, the high latency brought by non-trivial neighborhood data dependency limits GNNs in practical deployments. Conversely, the known ...
- short-paperJuly 2023
Embedding Based Retrieval in Friend Recommendation
- Jiahui Shi,
- Vivek Chaurasiya,
- Yozen Liu,
- Shubham Vij,
- Yan Wu,
- Satya Kanduri,
- Neil Shah,
- Peicheng Yu,
- Nik Srivastava,
- Lei Shi,
- Ganesh Venkataraman,
- Jun Yu
SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information RetrievalJuly 2023, Pages 3330–3334https://doi.org/10.1145/3539618.3591848Friend 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 ...
- research-articleApril 2023
Cultural Differences in Friendship Network Behaviors: A Snapchat Case Study
CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing SystemsApril 2023, Article No.: 671, Pages 1–14https://doi.org/10.1145/3544548.3581074Culture shapes people’s behavior, both online and offline. Surprisingly, there is sparse research on how cultural context affects network formation and content consumption on social media. We analyzed the friendship networks and dyadic relations between ...
- research-articleApril 2023
Reciprocity, Homophily, and Social Network Effects in Pictorial Communication: A Case Study of Bitmoji Stickers
- Julie Jiang,
- Ron Dotsch,
- Mireia Triguero Roura,
- Yozen Liu,
- Vítor Silva,
- Maarten W. Bos,
- Francesco Barbieri
CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing SystemsApril 2023, Article No.: 675, Pages 1–14https://doi.org/10.1145/3544548.3580990Pictorial emojis and stickers are commonly used in online social communications. We analyzed social communications using Bitmoji stickers, which are expressive pictorial stickers made from avatars resembling actual users. We collect a large-scale ...
- research-articleFebruary 2023
Graph Explicit Neural Networks: Explicitly Encoding Graphs for Efficient and Accurate Inference
WSDM '23: Proceedings of the Sixteenth ACM International Conference on Web Search and Data MiningFebruary 2023, Pages 348–356https://doi.org/10.1145/3539597.3570388As the state-of-the-art graph learning models, the message passing based neural networks (MPNNs) implicitly use the graph topology as the "pathways" to propagate node features. This implicit use of graph topology induces the MPNNs' over-reliance on (node)...
- research-articleApril 2024
GStarX: explaining graph neural networks with structure-aware cooperative games
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsNovember 2022, Article No.: 1440, Pages 19810–19823Explaining machine learning models is an important and increasingly popular area of research interest. The Shapley value from game theory has been proposed as a prime approach to compute feature importance towards model predictions on images, text, ...
- research-articleFebruary 2022
Friend Story Ranking with Edge-Contextual Local Graph Convolutions
WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data MiningFebruary 2022, Pages 1007–1015https://doi.org/10.1145/3488560.3498398Social platforms have paved the way in creating new, modern ways for users to communicate with each other. In recent years, multiple platforms have introduced ''Stories'' features, which enable broadcasting of ephemeral multimedia content. Specifically, ...
- research-articleOctober 2021
A Unified View on Graph Neural Networks as Graph Signal Denoising
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge ManagementOctober 2021, Pages 1202–1211https://doi.org/10.1145/3459637.3482225Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data. A single GNN layer typically consists of a feature transformation and a feature aggregation operation. The former normally uses feed-forward ...
- research-articleMay 2021
AdverTiming Matters: Examining User Ad Consumption for Effective Ad Allocations on Social Media
- Koustuv Saha,
- Yozen Liu,
- Nicholas Vincent,
- Farhan Asif Chowdhury,
- Leonardo Neves,
- Neil Shah,
- Maarten W. Bos
CHI '21: Proceedings of the 2021 CHI Conference on Human Factors in Computing SystemsMay 2021, Article No.: 581, Pages 1–18https://doi.org/10.1145/3411764.3445394Showing ads delivers revenue for online content distributors, but ad exposure can compromise user experience and cause user fatigue and frustration. Correctly balancing ads with other content is imperative. Currently, ad allocation relies primarily on ...
- research-articleJune 2021
Graph Neural Networks for Friend Ranking in Large-scale Social Platforms
WWW '21: Proceedings of the Web Conference 2021April 2021, Pages 2535–2546https://doi.org/10.1145/3442381.3450120Graph Neural Networks (GNNs) have recently enabled substantial advances in graph learning. Despite their rich representational capacity, GNNs remain under-explored for large-scale social modeling applications. One such industrially ubiquitous ...
- research-articleAugust 2020
Knowing your FATE: Friendship, Action and Temporal Explanations for User Engagement Prediction on Social Apps
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningAugust 2020, Pages 2269–2279https://doi.org/10.1145/3394486.3403276With the rapid growth and prevalence of social network applications (Apps) in recent years, understanding user engagement has become increasingly important, to provide useful insights for future App design and development. While several promising neural ...
- research-articleJuly 2019
Characterizing and Forecasting User Engagement with In-App Action Graph: A Case Study of Snapchat
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningJuly 2019, Pages 2023–2031https://doi.org/10.1145/3292500.3330750While mobile social apps have become increasingly important in people's daily life, we have limited understanding on what motivates users to engage with these apps. In this paper, we answer the question whether users' in-app activity patterns help ...