Adversarial Sampling and Training for Semi-Supervised Information Retrieval

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.

[1]  Shin Ishii,et al.  Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Lars Schmidt-Thieme,et al.  BPR: Bayesian Personalized Ranking from Implicit Feedback , 2009, UAI.

[3]  Bhaskar Mitra,et al.  Query Auto-Completion for Rare Prefixes , 2015, CIKM.

[4]  Bowen Zhou,et al.  Attentive Pooling Networks , 2016, ArXiv.

[5]  Bowen Zhou,et al.  Applying deep learning to answer selection: A study and an open task , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[6]  Madian Khabsa,et al.  Adversarial Training for Community Question Answer Selection Based on Multi-scale Matching , 2018, AAAI.

[7]  Dae Hoon Park,et al.  A Neural Language Model for Query Auto-Completion , 2017, SIGIR.

[8]  Alessandro Moschitti,et al.  Modeling Relational Information in Question-Answer Pairs with Convolutional Neural Networks , 2016, ArXiv.

[9]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.

[10]  Gregory N. Hullender,et al.  Learning to rank using gradient descent , 2005, ICML.

[11]  Filip Radlinski,et al.  Query chains: learning to rank from implicit feedback , 2005, KDD '05.

[12]  M. de Rijke,et al.  A Neural Click Model for Web Search , 2016, WWW.

[13]  Larry P. Heck,et al.  Learning deep structured semantic models for web search using clickthrough data , 2013, CIKM.

[14]  Jimmy J. Lin,et al.  Noise-Contrastive Estimation for Answer Selection with Deep Neural Networks , 2016, CIKM.

[15]  W. Bruce Croft,et al.  A Deep Relevance Matching Model for Ad-hoc Retrieval , 2016, CIKM.

[16]  Quanshi Zhang,et al.  Interpretable Convolutional Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[17]  Andrew M. Dai,et al.  Adversarial Training Methods for Semi-Supervised Text Classification , 2016, ICLR.

[18]  Fabrizio Silvestri,et al.  Context- and Content-aware Embeddings for Query Rewriting in Sponsored Search , 2015, SIGIR.

[19]  David A. McAllester,et al.  Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence , 2009, UAI 2009.

[20]  Alexandros Karatzoglou,et al.  Recurrent Neural Networks with Top-k Gains for Session-based Recommendations , 2017, CIKM.

[21]  Kai Xu,et al.  Interpreting Deep Classifier by Visual Distillation of Dark Knowledge , 2018, ArXiv.

[22]  Patrick Seemann,et al.  Matrix Factorization Techniques for Recommender Systems , 2014 .

[23]  Thomas Hofmann,et al.  Learning to Rank with Nonsmooth Cost Functions , 2006, NIPS.

[24]  David Warde-Farley,et al.  1 Adversarial Perturbations of Deep Neural Networks , 2016 .

[25]  Shin Ishii,et al.  Distributional Smoothing with Virtual Adversarial Training , 2015, ICLR 2016.

[26]  Di Wang,et al.  A Long Short-Term Memory Model for Answer Sentence Selection in Question Answering , 2015, ACL.

[27]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[28]  Tao Qin,et al.  Introducing LETOR 4.0 Datasets , 2013, ArXiv.

[29]  Thorsten Joachims,et al.  Accurately Interpreting Clickthrough Data as Implicit Feedback , 2017 .

[30]  Peng Zhang,et al.  IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models , 2017, SIGIR.

[31]  Xiaoyu Du,et al.  Adversarial Personalized Ranking for Recommendation , 2018, SIGIR.

[32]  Jakob Grue Simonsen,et al.  A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion , 2015, CIKM.

[33]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[34]  Christopher J. C. Burges,et al.  From RankNet to LambdaRank to LambdaMART: An Overview , 2010 .

[35]  Andrew M. Dai,et al.  Virtual Adversarial Training for Semi-Supervised Text Classification , 2016, ArXiv.

[36]  Weinan Zhang,et al.  LambdaFM: Learning Optimal Ranking with Factorization Machines Using Lambda Surrogates , 2016, CIKM.

[37]  Jun Wang,et al.  Optimizing top-n collaborative filtering via dynamic negative item sampling , 2013, SIGIR.

[38]  Tie-Yan Liu,et al.  Learning to Rank for Information Retrieval , 2011 .

[39]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[40]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[41]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[42]  Xuehua Shen,et al.  Context-sensitive information retrieval using implicit feedback , 2005, SIGIR '05.

[43]  Steffen Rendle,et al.  Improving pairwise learning for item recommendation from implicit feedback , 2014, WSDM.

[44]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[45]  Depeng Jin,et al.  An Improved Sampler for Bayesian Personalized Ranking by Leveraging View Data , 2018, WWW.