Understanding the Effects of Adversarial Personalized Ranking
Optimization Method on Recommendation Quality
- URL: http://arxiv.org/abs/2107.13876v1
- Date: Thu, 29 Jul 2021 10:22:20 GMT
- Title: Understanding the Effects of Adversarial Personalized Ranking
Optimization Method on Recommendation Quality
- Authors: Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Felice Antonio
Merra
- Abstract summary: We model the learning characteristics of the Bayesian Personalized Ranking (BPR) and APR optimization frameworks.
We show that APR amplifies the popularity bias more than BPR due to an unbalanced number of received positive updates from short-head items.
- Score: 6.197934754799158
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recommender systems (RSs) employ user-item feedback, e.g., ratings, to match
customers to personalized lists of products. Approaches to top-k recommendation
mainly rely on Learning-To-Rank algorithms and, among them, the most widely
adopted is Bayesian Personalized Ranking (BPR), which bases on a pair-wise
optimization approach. Recently, BPR has been found vulnerable against
adversarial perturbations of its model parameters. Adversarial Personalized
Ranking (APR) mitigates this issue by robustifying BPR via an adversarial
training procedure. The empirical improvements of APR's accuracy performance on
BPR have led to its wide use in several recommender models. However, a key
overlooked aspect has been the beyond-accuracy performance of APR, i.e.,
novelty, coverage, and amplification of popularity bias, considering that
recent results suggest that BPR, the building block of APR, is sensitive to the
intensification of biases and reduction of recommendation novelty. In this
work, we model the learning characteristics of the BPR and APR optimization
frameworks to give mathematical evidence that, when the feedback data have a
tailed distribution, APR amplifies the popularity bias more than BPR due to an
unbalanced number of received positive updates from short-head items. Using
matrix factorization (MF), we empirically validate the theoretical results by
performing preliminary experiments on two public datasets to compare BPR-MF and
APR-MF performance on accuracy and beyond-accuracy metrics. The experimental
results consistently show the degradation of novelty and coverage measures and
a worrying amplification of bias.
Related papers
- Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.
To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.
Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
arXiv Detail & Related papers (2024-05-26T05:38:50Z) - Augmenting Unsupervised Reinforcement Learning with Self-Reference [63.68018737038331]
Humans possess the ability to draw on past experiences explicitly when learning new tasks.
We propose the Self-Reference (SR) approach, an add-on module explicitly designed to leverage historical information.
Our approach achieves state-of-the-art results in terms of Interquartile Mean (IQM) performance and Optimality Gap reduction on the Unsupervised Reinforcement Learning Benchmark.
arXiv Detail & Related papers (2023-11-16T09:07:34Z) - Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal
Review Helpfulness Prediction [40.09991896766369]
Multimodal Review Helpfulness Prediction aims to rank product reviews based on predicted helpfulness scores.
We propose a listwise attention network that clearly captures the MRHP ranking context.
We also propose gradient-boosted decision tree as the score predictor to efficaciously partition product reviews' representations.
arXiv Detail & Related papers (2023-05-22T03:31:00Z) - Improving Recommendation Fairness via Data Augmentation [66.4071365614835]
Collaborative filtering based recommendation learns users' preferences from all users' historical behavior data, and has been popular to facilitate decision making.
A recommender system is considered unfair when it does not perform equally well for different user groups according to users' sensitive attributes.
In this paper, we study how to improve recommendation fairness from the data augmentation perspective.
arXiv Detail & Related papers (2023-02-13T13:11:46Z) - Item-based Variational Auto-encoder for Fair Music Recommendation [1.8782288713227568]
The EvalRS DataChallenge aims to build a more realistic recommender system considering accuracy, fairness, and diversity in evaluation.
Our proposed system is based on an ensemble between an item-based variational auto-encoder (VAE) and a Bayesian personalized ranking matrix factorization (BPRMF)
arXiv Detail & Related papers (2022-10-24T06:42:16Z) - Off-policy evaluation for learning-to-rank via interpolating the
item-position model and the position-based model [83.83064559894989]
A critical need for industrial recommender systems is the ability to evaluate recommendation policies offline, before deploying them to production.
We develop a new estimator that mitigates the problems of the two most popular off-policy estimators for rankings.
In particular, the new estimator, called INTERPOL, addresses the bias of a potentially misspecified position-based model.
arXiv Detail & Related papers (2022-10-15T17:22:30Z) - Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation [59.500347564280204]
We propose a new Aleatoric Uncertainty-aware Recommendation (AUR) framework.
AUR consists of a new uncertainty estimator along with a normal recommender model.
As the chance of mislabeling reflects the potential of a pair, AUR makes recommendations according to the uncertainty.
arXiv Detail & Related papers (2022-09-22T04:32:51Z) - Debiasing Neural Retrieval via In-batch Balancing Regularization [25.941718123899356]
We develop a differentiable textitnormed Pairwise Ranking Fairness (nPRF) and leverage the T-statistics on top of nPRF to improve fairness.
Our method with nPRF achieves significantly less bias with minimal degradation in ranking performance compared with the baseline.
arXiv Detail & Related papers (2022-05-18T22:57:15Z) - Cross Pairwise Ranking for Unbiased Item Recommendation [57.71258289870123]
We develop a new learning paradigm named Cross Pairwise Ranking (CPR)
CPR achieves unbiased recommendation without knowing the exposure mechanism.
We prove in theory that this way offsets the influence of user/item propensity on the learning.
arXiv Detail & Related papers (2022-04-26T09:20:27Z) - Debiased Explainable Pairwise Ranking from Implicit Feedback [0.3867363075280543]
We focus on the state of the art pairwise ranking model, Bayesian Personalized Ranking (BPR)
BPR is a black box model that does not explain its outputs, thus limiting the user's trust in the recommendations.
We propose a novel explainable loss function and a corresponding Matrix Factorization-based model that generates recommendations along with item-based explanations.
arXiv Detail & Related papers (2021-07-30T17:19:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.