# Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items

arXiv: https://arxiv.org/abs/2507.22268 · HTML: https://mlsanity.com/paper/2507.22268/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [LINE: Large-scale Information Network Embedding](https://mlsanity.com/paper/1503.03578/) (2015)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Self-supervised Graph Learning for Recommendation](https://mlsanity.com/paper/2010.10783/) (2020)
- [Inferring Networks of Substitutable and Complementary Products](https://mlsanity.com/paper/1506.08839/) (2015)
- [Representation Learning for Attributed Multiplex Heterogeneous Network](https://mlsanity.com/paper/1905.01669/) (2019)
- [Multimodal Recommender Systems: A Survey](https://mlsanity.com/paper/2302.03883/) (2023)
- [Try This Instead: Personalized and Interpretable Substitute Recommendation](https://mlsanity.com/paper/2005.09344/) (2020)
- [LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation](https://mlsanity.com/paper/2410.21520/) (2024)
- [A Pre-trained Sequential Recommendation Framework: Popularity Dynamics for Zero-shot Transfer](https://mlsanity.com/paper/2401.01497/) (2024)
- [Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework](https://mlsanity.com/paper/2009.05197/) (2020)
- [Co-clustering for Federated Recommender System](https://mlsanity.com/paper/2411.01690/) (2024)
- [LLM-RecG: A Semantic Bias-Aware Framework for Zero-Shot Sequential Recommendation](https://mlsanity.com/paper/2501.19232/) (2025)
- [A Transformer-Based Substitute Recommendation Model Incorporating Weakly Supervised Customer Behavior Data](https://mlsanity.com/paper/2211.02533/) (2022)
- [Robust Basket Recommendation via Noise-tolerated Graph Contrastive Learning](https://mlsanity.com/paper/2311.16334/) (2023)

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

- [SafeImpute: Reliable Clinical Data Imputation via Conformal Selection](https://mlsanity.com/paper/2607.05613/) (2026)
- [Beyond Co-purchase Relation: Evolution of Complementary Recommendations at Allegro](https://mlsanity.com/paper/2609.05063/) (2026)

## Abstract (arXiv)

We study the problem of inferring substitutable and complementary items, which underpins applications such as alternative and follow-up purchase suggestions. Existing approaches typically learn from behavior-derived item-item associations using GNNs or leverage item content alone. However, these methods often overlook two key challenges: (i) user behaviors (e.g., co-view/co-purchase) only provide noisy weak supervision, and (ii) behavior signals are long-tailed, leaving many items with sparse associations. We propose MMSC, a self-supervised multi-modal relational representation learning framework that combines a multi-modal foundation model adapted to encode item metadata and a self-supervised denoising module that learns relationship-aware representations from noisy user behaviors, unified by a hierarchical aggregation mechanism. We further use LLM-assisted supervision to mitigate noise in behavior-derived supervision during training. Experiments on five real-world datasets show that MMSC consistently outperforms existing baselines by 26.1% for substitutable and 39.2% for complementary item inference, while remaining effective for cold-start items. We share our code for reproducibility.