# Mitigating Filter Bubbles within Deep Recommender Systems

arXiv: https://arxiv.org/abs/2209.08180 · HTML: https://mlsanity.com/paper/2209.08180/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 10 references that are in the map.
- First posted on arXiv 16 Sep 2022.

## Builds on (most cited first, 3 of 3)

- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [Item2Vec: Neural Item Embedding for Collaborative Filtering](https://mlsanity.com/paper/1603.04259/) (2016)

## Built on by (most cited first, 2 of 2)

- [Avoiding Over-Personalization with Rule-Guided Knowledge Graph Adaptation for LLM Recommendations](https://mlsanity.com/paper/2509.07133/) (2025)
- [Ideological Isolation in Online Social Networks: A Survey of Computational Definitions, Metrics, and Mitigation Strategies](https://mlsanity.com/paper/2601.07884/) (2026)

## Abstract (arXiv)

Recommender systems, which offer personalized suggestions to users, power many of today's social media, e-commerce and entertainment. However, these systems have been known to intellectually isolate users from a variety of perspectives, or cause filter bubbles. In our work, we characterize and mitigate this filter bubble effect. We do so by classifying various datapoints based on their user-item interaction history and calculating the influences of the classified categories on each other using the well known TracIn method. Finally, we mitigate this filter bubble effect without compromising accuracy by carefully retraining our recommender system.