# Negative Feedback for Music Personalization

arXiv: https://arxiv.org/abs/2406.04488 · HTML: https://mlsanity.com/paper/2406.04488/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 6 Jun 2024.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba](https://mlsanity.com/paper/1803.02349/) (2018)
- [On the Effectiveness of Sampled Softmax Loss for Item Recommendation](https://mlsanity.com/paper/2201.02327/) (2022)
- [gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling](https://mlsanity.com/paper/2308.07192/) (2023)
- [The Music Streaming Sessions Dataset](https://mlsanity.com/paper/1901.09851/) (2018)
- [Scaling Session-Based Transformer Recommendations using Optimized Negative Sampling and Loss Functions](https://mlsanity.com/paper/2307.14906/) (2023)
- [Augmented Negative Sampling for Collaborative Filtering](https://mlsanity.com/paper/2308.05972/) (2023)
- [Learning from Negative User Feedback and Measuring Responsiveness for Sequential Recommenders](https://mlsanity.com/paper/2308.12256/) (2023)
- [Why People Skip Music? On Predicting Music Skips using Deep Reinforcement Learning](https://mlsanity.com/paper/2301.03881/) (2023)
- [Evaluating Music Recommendations with Binary Feedback for Multiple Stakeholders](https://mlsanity.com/paper/2109.07692/) (2021)
- [Leveraging Negative Signals with Self-Attention for Sequential Music Recommendation](https://mlsanity.com/paper/2309.11623/) (2023)

## Abstract (arXiv)

Next-item recommender systems are often trained using only positive feedback with randomly-sampled negative feedback. We show the benefits of using real negative feedback both as inputs into the user sequence and also as negative targets for training a next-song recommender system for internet radio. In particular, using explicit negative samples during training helps reduce training time by ~60% while also improving test accuracy by ~6%; adding user skips as additional inputs also can considerably increase user coverage alongside slightly improving accuracy. We test the impact of using a large number of random negative samples to capture a 'harder' one and find that the test accuracy increases with more randomly-sampled negatives, but only to a point. Too many random negatives leads to false negatives that limits the lift, which is still lower than if using true negative feedback. We also find that the test accuracy is fairly robust with respect to the proportion of different feedback types, and compare the learned embeddings for different feedback types.