A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
PinnerSage creates multi-modal user embeddings for better Pinterest recommendations.
Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of items and hundreds of millions of users remains a challenge. Here we de…
Two-stage recommender systems show better performance when components interact rather than operate independently.
Model predicts web page parallelism for improved browser performance and energy.
RNE tackles scalable recommendation for billion-scale scenarios.