Awesome-Deep-Learning-Papers-for-Search-Recommendation-Advertising

Why we included this project

This reading list collects deep learning papers that cover the ranking pipeline in industrial search, recommendation, and advertising systems, organized by stage: embedding, matching, pre-ranking, ranking, post-ranking, relevance, LLM-based ranking, and reinforcement learning. That structure makes it easy to trace how a technique like word2vec or graph convolutional networks shows up in a production CTR or CVR model. The maintainers' own TOIS survey on deep learning to rank anchors the collection, so the list has a clear editorial point of view instead of just accumulating links. Teams tuning recommender systems will find a practical map of the literature, and researchers can track down the original papers behind common industrial techniques. It is a curated reference index rather than runnable software, so its value lies in the organization and selection.