A5037605408- Recommender Systems and Techniques
- Advanced Graph Neural Networks
- Caching and Content Delivery
- Topic Modeling
- Human Pose and Action Recognition
- Advanced Image and Video Retrieval Techniques
- Human Mobility and Location-Based Analysis
- Sentiment Analysis and Opinion Mining
- Digital Marketing and Social Media
- Auction Theory and Applications
- Domain Adaptation and Few-Shot Learning
- Video Analysis and Summarization
- Personal Information Management and User Behavior
- Multimodal Machine Learning Applications
- Advanced Bandit Algorithms Research
- Multi-Criteria Decision Making
- Game Theory and Voting Systems
- Complex Network Analysis Techniques
- Generative Adversarial Networks and Image Synthesis
Case Western Reserve University
2019
Graph convolutional networks (GCNs) are a powerful class of graph neural networks. Trained in semi-supervised end-to-end fashion, GCNs can learn to integrate node features and structures generate high-quality embeddings that be used for various downstream tasks like search recommendation. However, existing mostly work on homogeneous graphs consider single embedding each node, which do not sufficiently model the multi-facet nature complex interaction nodes real-world Here, we present...
Learned embeddings for products are an important building block web-scale e-commerce recommendation systems. At Pinterest, we build a single set of product called ItemSage to provide relevant recommendations in all shopping use cases including user, image and search based recommendations. This approach has led significant improvements engagement conversion metrics, while reducing both infrastructure maintenance cost. While most prior work focuses on from features coming modality, introduce...
Sequential models have become increasingly popular in powering personalized recommendation systems over the past several years. These approaches traditionally model a user's actions on website as sequence to predict next action. While theoretically simplistic, these are quite challenging deploy production, commonly requiring streaming infrastructure reflect latest user activity and potentially managing mutable data for encoding hidden state. Here we introduce PinnerFormer, representation...
Sequential models that encode user activity for next action prediction have become a popular design choice building web-scale personalized recommendation systems. Traditional methods of sequential either utilize end-to-end learning on realtime actions, or learn representations separately in an offline batch-generated manner. This paper (1) presents Pinterest's ranking architecture Homefeed, our product and the largest engagement surface; (2) proposes TransAct, model extracts users'...
Graph Convolutional Networks (GCN) can efficiently integrate graph structure and node features to learn high-quality embeddings. At Pinterest, we have developed deployed PinSage, a data-efficient GCN that learns pin embeddings from the Pin-Board graph. Pinterest relies heavily on PinSage which in turn only leverages However, there exist several entities at heterogeneous interactions among these entities. These diverse provide important signal for recommendations modeling. In this work, show...
In this paper, we present OmniSearchSage, a versatile and scalable system for understanding search queries, pins, products Pinterest search. We jointly learn unified query embedding coupled with pin product embeddings, leading to an improvement of $>8\%$ relevance, $>7\%$ engagement, $>5\%$ ads CTR in Pinterest's production system. The main contributors these gains are improved content understanding, better multi-task learning, real-time serving. enrich our entity representations using...
Sequential models have become increasingly popular in powering personalized recommendation systems over the past several years. These approaches traditionally model a user's actions on website as sequence to predict next action. While theoretically simplistic, these are quite challenging deploy production, commonly requiring streaming infrastructure reflect latest user activity and potentially managing mutable data for encoding hidden state. Here we introduce PinnerFormer, representation...
Graph Convolutional Networks (GCN) can efficiently integrate graph structure and node features to learn high-quality embeddings. These embeddings then be used for several tasks such as recommendation search. At Pinterest, we have developed deployed PinSage, a data-efficient GCN that learns pin from the Pin-Board graph. The contains board entities captures belongs interaction. However, there exist at Pinterest users, idea pins, creators, heterogeneous interactions among these add-to-cart,...
Sequential models that encode user activity for next action prediction have become a popular design choice building web-scale personalized recommendation systems. Traditional methods of sequential either utilize end-to-end learning on realtime actions, or learn representations separately in an offline batch-generated manner. This paper (1) presents Pinterest's ranking architecture Homefeed, our product and the largest engagement surface; (2) proposes TransAct, model extracts users'...
Learned embeddings for products are an important building block web-scale e-commerce recommendation systems. At Pinterest, we build a single set of product called ItemSage to provide relevant recommendations in all shopping use cases including user, image and search based recommendations. This approach has led significant improvements engagement conversion metrics, while reducing both infrastructure maintenance cost. While most prior work focuses on from features coming modality, introduce...
With the availability of fast internet and convenient imaging devices such as smart phones, videos are becoming increasingly popular important content on social media platforms recently. They widely adopted for various purposes including, but not limited to, advertisement, education entertainment. One problem in understanding is thumbnail generation, which involves selecting one or a few images, typically frames, representative given video. These thumbnails can then be used only summary...