# Representation Learning and Pairwise Ranking for Implicit Feedback in Recommendation Systems

arXiv: https://arxiv.org/abs/1705.00105 · HTML: https://mlsanity.com/paper/1705.00105/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2017.

## Built on by (most cited first, 11 of 11)

- [Learning Explicit User Interest Boundary for Recommendation](https://mlsanity.com/paper/2111.11026/) (2021)
- [Generalization bounds for learning under graph-dependence: A survey](https://mlsanity.com/paper/2203.13534/) (2022)
- [From "Thumbs Up" to "10 out of 10": Reconsidering Scalar Feedback in Interactive Reinforcement Learning](https://mlsanity.com/paper/2311.10284/) (2023)
- [Enriching Artificial Intelligence Explanations with Knowledge Fragments](https://mlsanity.com/paper/2204.05579/) (2022)
- [Adaptive Latent Factor Analysis via Generalized Momentum-Incorporated Particle Swarm Optimization](https://mlsanity.com/paper/2208.02423/) (2022)
- [Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systems](https://mlsanity.com/paper/2506.22648/) (2025)
- [Sparsity Regularization For Cold-Start Recommendation](https://mlsanity.com/paper/2201.10711/) (2022)
- [Learning over No-Preferred and Preferred Sequence of Items for Robust Recommendation (Extended Abstract)](https://mlsanity.com/paper/2202.13240/) (2022)
- [Inference and Optimization for Engineering and Physical Systems](https://mlsanity.com/paper/2208.13880/) (2022)
- [Data-Driven Stochastic AC-OPF using Gaussian Processes](https://mlsanity.com/paper/2402.11365/) (2024)
- [Fast and Featureless Node Representation Learning with Partial Pairwise Supervision](https://mlsanity.com/paper/2605.19916/) (2026)

## Abstract (arXiv)

In this paper, we propose a novel ranking framework for collaborative filtering with the overall aim of learning user preferences over items by minimizing a pairwise ranking loss. We show the minimization problem involves dependent random variables and provide a theoretical analysis by proving the consistency of the empirical risk minimization in the worst case where all users choose a minimal number of positive and negative items. We further derive a Neural-Network model that jointly learns a new representation of users and items in an embedded space as well as the preference relation of users over the pairs of items. The learning objective is based on three scenarios of ranking losses that control the ability of the model to maintain the ordering over the items induced from the users' preferences, as well as, the capacity of the dot-product defined in the learned embedded space to produce the ordering. The proposed model is by nature suitable for implicit feedback and involves the estimation of only very few parameters. Through extensive experiments on several real-world benchmarks on implicit data, we show the interest of learning the preference and the embedding simultaneously when compared to learning those separately. We also demonstrate that our approach is very competitive with the best state-of-the-art collaborative filtering techniques proposed for implicit feedback.