# Interpretable Triplet Importance for Personalized Ranking

arXiv: https://arxiv.org/abs/2407.19469 · HTML: https://mlsanity.com/paper/2407.19469/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 48 references that are in the map.
- First posted on arXiv 28 Jul 2024.

## Builds on (most cited first, 21 of 21)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [Implicit Regularization in Deep Matrix Factorization](https://mlsanity.com/paper/1905.13655/) (2019)
- [Monte Carlo Gradient Estimation in Machine Learning](https://mlsanity.com/paper/1906.10652/) (2019)
- [Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning](https://mlsanity.com/paper/2110.14049/) (2021)
- [Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms](https://mlsanity.com/paper/1908.08619/) (2019)
- [Neuron Shapley: Discovering the Responsible Neurons](https://mlsanity.com/paper/2002.09815/) (2020)
- [Yelp Dataset Challenge: Review Rating Prediction](https://mlsanity.com/paper/1605.05362/) (2016)
- [A Distributional Framework for Data Valuation](https://mlsanity.com/paper/2002.12334/) (2020)
- [Denoising Implicit Feedback for Recommendation](https://mlsanity.com/paper/2006.04153/) (2020)
- [Towards Understanding the Overfitting Phenomenon of Deep Click-Through Rate Prediction Models](https://mlsanity.com/paper/2209.06053/) (2022)
- [CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification](https://mlsanity.com/paper/2211.06800/) (2022)
- [Multi-Graph Convolution Collaborative Filtering](https://mlsanity.com/paper/2001.00267/) (2020)
- [Dynamically Expandable Graph Convolution for Streaming Recommendation](https://mlsanity.com/paper/2303.11700/) (2023)
- [Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender System](https://mlsanity.com/paper/2308.07760/) (2023)
- [Reweighting Clicks with Dwell Time in Recommendation](https://mlsanity.com/paper/2209.09000/) (2022)
- [Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation](https://mlsanity.com/paper/2208.01709/) (2022)

## Built on by (most cited first, 1 of 1)

- [Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption](https://mlsanity.com/paper/2605.30089/) (2026)

## Abstract (arXiv)

Personalized item ranking has been a crucial component contributing to the performance of recommender systems. As a representative approach, pairwise ranking directly optimizes the ranking with user implicit feedback by constructing (textituser, textitpositive item, textitnegative item) triplets. Several recent works have noticed that treating all triplets equally may hardly achieve the best effects. They assign different importance scores to negative items, user-item pairs, or triplets, respectively. However, almost all the generated importance scores are groundless and hard to interpret, thus far from trustworthy and transparent. To tackle these, we propose the textitTriplet Shapley -- a Shapely value-based method to measure the triplet importance in an interpretable manner. Due to the huge number of triplets, we transform the original Shapley value calculation to the Monte Carlo (MC) approximation, where the guarantee for the approximation unbiasedness is also provided. To stabilize the MC approximation, we adopt a control covariates-based method. Finally, we utilize the triplet Shapley value to guide the resampling of important triplets for benefiting the model learning. Extensive experiments are conducted on six public datasets involving classical matrix factorization- and graph neural network-based recommendation models. Empirical results and subsequent analysis show that our model consistently outperforms the state-of-the-art methods.