Adversarial Sampling and Training for Semi-Supervised Information Retrieval

Abstract

Ad-hoc retrieval models with implicit feedback often have problems, e.g., the imbalanced classes in the data set. Too few clicked documents may hurt generalization ability of the models, whereas too many non-clicked documents may harm effectiveness of the models and efficiency of training. In addition, recent neural network-based models are vulnerable to adversarial examples due to the linear nature in them. To solve the problems at the same time, we propose an adversarial sampling and training framework to learn ad-hoc retrieval models with implicit feedback. Our key idea is (i) to augment clicked examples by adversarial training for better generalization and (ii) to obtain very informational non-clicked examples by adversarial sampling and training. Experiments are performed on benchmark data sets for common ad-hoc retrieval tasks such as Web search, item recommendation, and question answering. Experimental results indicate that the proposed approaches significantly outperform strong baselines especially for high-ranked documents, and they outperform IRGAN in NDCG@5 using only 5% of labeled data for the Web search task.

Published in WWW 2019

References in corpus (4)

• Recurrent Neural Networks with Top-k Gains for Session-based Recommendations
• A Deep Relevance Matching Model for Ad-hoc Retrieval
• IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models
• Adversarial Personalized Ranking for Recommendation

Cited by in corpus (12)

• Reinforced Negative Sampling over Knowledge Graph for Recommendation
• Semantic Models for the First-stage Retrieval: A Comprehensive Review
• Self-Guided Learning to Denoise for Robust Recommendation
• On the Theories Behind Hard Negative Sampling for Recommendation
• Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling
• Learning Explicit User Interest Boundary for Recommendation
• Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering
• Learning To Rank Resources with GNN
• Regularized Adversarial Sampling and Deep Time-aware Attention for Click-Through Rate Prediction
• Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrieval
• MixDec Sampling: A Soft Link-based Sampling Method of Graph Neural Network for Recommendation
• ESANS: Effective and Semantic-Aware Negative Sampling for Large-Scale Retrieval Systems