Evaluation Framework for Understanding Sensitive Attribute Association Bias in Latent Factor Recommendation Algorithms
We present a novel evaluation framework for representation bias in latent factor recommendation (LFR) algorithms. Our framework introduces the concept of attribute association bias in recommendations allowing practitioners to explore how recommendation systems can introduce or amplify stakeholder representation harm. Attribute association bias (AAB) occurs when sensitive attributes become semantically captured or entangled in the trained recommendation latent space. This bias can result in the recommender reinforcing harmful stereotypes, which may result in downstream representation harms to system consumer and provider stakeholders. LFR models are at risk of experiencing AAB due to their ability to entangle explicit and implicit attributes into the trained latent space. Understanding this phenomenon is essential due to the increasingly common use of entity vectors as attributes in downstream components in hybrid industry recommendation systems. We provide practitioners with a framework for executing disaggregated evaluations of AAB within broader algorithmic auditing frameworks. Inspired by research in natural language processing (NLP) observing gender bias in word embeddings, our framework introduces AAB evaluation methods specifically for recommendation entity vectors. We present four evaluation strategies for sensitive AAB in LFR models: attribute bias directions, attribute association bias metrics, classification for explaining bias, and latent space visualization. We demonstrate the utility of our framework by evaluating user gender AAB regarding podcast genres with an industry case study of a production-level DNN recommendation model. We uncover significant levels of user gender AAB when user gender is used and removed as a model feature during training, pointing to the potential for systematic bias in LFR model outputs.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeRecommendation SystemsWord EmbeddingsSimilar Papers 제목 키워드 기반
SALMUBench: A Benchmark for Sensitive Association-Level Multimodal Unlearning
As multimodal models like CLIP become integral to downstream systems, the need to remove sensitive information is critical. However, machine unlearning for contrastively-trained encoders remains underexplored, and existi…
NeuroLIP: Interpretable and Fair Cross-Modal Alignment of fMRI and Phenotypic Text
Integrating functional magnetic resonance imaging (fMRI) connectivity data with phenotypic textual descriptors (e.g., disease label, demographic data) holds significant potential to advance our understanding of neurologi…
AttributeContrastive Learningcross-modal alignmentDiagnostic+2Enhancing Fairness in Unsupervised Graph Anomaly Detection through Disentanglement
Graph anomaly detection (GAD) is increasingly crucial in various applications, ranging from financial fraud detection to fake news detection. However, current GAD methods largely overlook the fairness problem, which migh…
Anomaly DetectionDecision MakingDisentanglementFairness+5How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions
Text-to-image generative models often exhibit bias related to sensitive attributes. However, current research tends to focus narrowly on single-object prompts with limited contextual diversity. In reality, each object or…
CFaiRLLM: Consumer Fairness Evaluation in Large-Language Model Recommender System
This work takes a critical stance on previous studies concerning fairness evaluation in Large Language Model (LLM)-based recommender systems, which have primarily assessed consumer fairness by comparing recommendation li…
AttributeFairnessLanguage ModelingLanguage Modelling+3