# An Image Dataset for Benchmarking Recommender Systems with Raw Pixels

arXiv: https://arxiv.org/abs/2309.06789 · HTML: https://mlsanity.com/paper/2309.06789/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2023.

## Built on by (most cited first, 18 of 18)

- [HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling](https://mlsanity.com/paper/2409.12740/) (2024)
- [A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval](https://mlsanity.com/paper/2503.05659/) (2025)
- [IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT](https://mlsanity.com/paper/2404.02059/) (2024)
- [MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning](https://mlsanity.com/paper/2601.22416/) (2026)
- [Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation](https://mlsanity.com/paper/2411.02992/) (2024)
- [A Survey on Large Language Models in Multimodal Recommender Systems](https://mlsanity.com/paper/2505.09777/) (2025)
- [MoTime: A Dataset Suite for Multimodal Time Series Forecasting](https://mlsanity.com/paper/2505.15072/) (2025)
- [Adversarial Item Promotion on Visually-Aware Recommender Systems by Guided Diffusion](https://mlsanity.com/paper/2312.15826/) (2023)
- [Diffusion Models in Recommendation Systems: A Survey](https://mlsanity.com/paper/2501.10548/) (2025)
- [Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-Head Decoding](https://mlsanity.com/paper/2511.10492/) (2025)
- [ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation](https://mlsanity.com/paper/2606.28357/) (2026)
- [RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation](https://mlsanity.com/paper/2509.03131/) (2025)
- [ITDR: An Instruction Tuning Dataset for Enhancing Large Language Models in Recommendations](https://mlsanity.com/paper/2508.05667/) (2025)
- [ORBIT -- Open Recommendation Benchmark for Reproducible Research with Hidden Tests](https://mlsanity.com/paper/2510.26095/) (2025)
- [T-RoPE: Time-Aware Rotary Position Embedding for Sequential Recommendation](https://mlsanity.com/paper/2609.30576/) (2026)
- [Generate, Not Recommend: Personalized Multimodal Content Generation](https://mlsanity.com/paper/2506.01704/) (2025)
- [TSPORec: Token Selection via Preference Optimization for LLM-Based Sequential Recommendation](https://mlsanity.com/paper/2608.09605/) (2026)
- [MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision](https://mlsanity.com/paper/2610.17856/) (2026)

## Abstract (arXiv)

Recommender systems (RS) have achieved significant success by leveraging explicit identification (ID) features. However, the full potential of content features, especially the pure image pixel features, remains relatively unexplored. The limited availability of large, diverse, and content-driven image recommendation datasets has hindered the use of raw images as item representations. In this regard, we present PixelRec, a massive image-centric recommendation dataset that includes approximately 200 million user-image interactions, 30 million users, and 400,000 high-quality cover images. By providing direct access to raw image pixels, PixelRec enables recommendation models to learn item representation directly from them. To demonstrate its utility, we begin by presenting the results of several classical pure ID-based baseline models, termed IDNet, trained on PixelRec. Then, to show the effectiveness of the dataset's image features, we substitute the itemID embeddings (from IDNet) with a powerful vision encoder that represents items using their raw image pixels. This new model is dubbed PixelNet.Our findings indicate that even in standard, non-cold start recommendation settings where IDNet is recognized as highly effective, PixelNet can already perform equally well or even better than IDNet. Moreover, PixelNet has several other notable advantages over IDNet, such as being more effective in cold-start and cross-domain recommendation scenarios. These results underscore the importance of visual features in PixelRec. We believe that PixelRec can serve as a critical resource and testing ground for research on recommendation models that emphasize image pixel content. The dataset, code, and leaderboard will be available at https://github.com/westlake-repl/PixelRec.