ABSTRACT
In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss has been extended to language modeling and recommendation, two fields that fall into the framework of learning from Positive and Unlabeled data.
In this paper, we stress the different drawbacks of the current family of softmax losses and sampling schemes when applied in a Positive and Unlabeled learning setup. We propose both a Relaxed Softmax loss (RS) and a new negative sampling scheme based on Boltzmann formulation. We show that the new training objective is better suited for the tasks of density estimation, item similarity and next-event prediction by driving uplifts in performance on textual and recommendation datasets against classical softmax.
- Philip Bachman, Alessandro Sordoni, and Adam Trischler. 2017. Learning algorithms for active learning. In Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 301--310. Google ScholarDigital Library
- Yoshua Bengio, Réjean Ducharme, Pascal Vincent, and Christian Jauvin. 2003. A neural probabilistic language model. Journal of machine learning research 3, Feb (2003), 1137--1155. Google Scholar
- Yoshua Bengio and Jean-Sébastien Senécal. 2008. Adaptive importance sampling to accelerate training of a neural probabilistic language model. IEEE Transactions on Neural Networks 19, 4 (2008), 713--722. Google ScholarDigital Library
- Yoshua Bengio, Jean-Sébastien Senécal, et al. 2003. Quick Training of Probabilistic Neural Nets by Importance Sampling.. In AISTATS. 1--9.Google Scholar
- David M Blei, Andrew Y Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research 3, Jan (2003), 993--1022. Google ScholarDigital Library
- Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2016. Enriching Word Vectors with Subword Information. CoRR abs/1607.04606 (2016). arXiv:1607.04606 http://arxiv.org/abs/1607.04606Google Scholar
- Long Chen, Fajie Yuan, Joemon M Jose, and Weinan Zhang. 2018. Improving Negative Sampling for Word Representation using Self-embedded Features. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining. ACM, 99--107. Google ScholarDigital Library
- Charles Elkan and Keith Noto. 2008. Learning classifiers from only positive and unlabeled data. In Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 213--220. Google ScholarDigital Library
- Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 855--864. Google ScholarDigital Library
- M. Gutmann and A. Hyvärinen. 2010. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. JMLR WCP, Vol. 9. Journal of Machine Learning Research - Proceedings Track, 297--304.Google Scholar
- Tzu-Kuo Huang, Alekh Agarwal, Daniel J Hsu, John Langford, and Robert E Schapire. 2015. Efficient and parsimonious agnostic active learning. In Advances in Neural Information Processing Systems. 2755--2763. Google ScholarDigital Library
- Sébastien Jean, Kyunghyun Cho, Roland Memisevic, and Yoshua Bengio. 2014. On Using Very Large Target Vocabulary for Neural Machine Translation. CoRR abs/1412.2007 (2014). arXiv:1412.2007 http://arxiv.org/abs/1412.2007Google Scholar
- Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. 2016. Bag of Tricks for Efficient Text Classification. CoRR abs/1607.01759 (2016). arXiv:1607.01759Google Scholar
- Christoph Käding, Alexander Freytag, Erik Rodner, Andrea Perino, and Joachim Denzler. 2016. Large-scale active learning with approximations of expected model output changes. In German Conference on Pattern Recognition. Springer, 179--191.Google ScholarCross Ref
- Quoc Le and Tomas Mikolov. 2014. Distributed representations of sentences and documents. In International Conference on Machine Learning. 1188--1196. Google ScholarDigital Library
- Hai Le Son, Alexandre Allauzen, and François Yvon. 2012. Measuring the influence of long range dependencies with neural network language models. In Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT. Association for Computational Linguistics, 1--10. Google ScholarDigital Library
- Wee Sun Lee and Bing Liu. 2003. Learning with positive and unlabeled examples using weighted logistic regression. In ICML, Vol. 3. 448--455. Google ScholarDigital Library
- Xiaoli Li and Bing Liu. 2003. Learning to classify texts using positive and unlabeled data. In IJCAI, Vol. 3. 587--592. Google ScholarDigital Library
- Xiao-Li Li and Bing Liu. 2005. Learning from positive and unlabeled examples with different data distributions. In European Conference on Machine Learning. Springer, 218--229. Google ScholarDigital Library
- Dawen Liang, Laurent Charlin, James McInerney, and David M Blei. 2016. Modeling user exposure in recommendation. In Proceedings of the 25th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 951--961. Google ScholarDigital Library
- Bing Liu, Wee Sun Lee, Philip S Yu, and Xiaoli Li. 2002. Partially supervised classification of text documents. In ICML, Vol. 2. Citeseer, 387--394. Google ScholarDigital Library
- Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013).Google Scholar
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119. Google ScholarDigital Library
- Tomas Mikolov and Geoffrey Zweig. 2012. Context dependent recurrent neural network language model. (2012).Google Scholar
- Andriy Mnih and Yee Whye Teh. 2012. A fast and simple algorithm for training neural probabilistic language models. arXiv preprint arXiv:1206.6426 (2012). Google ScholarDigital Library
- Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu, and Santhoshkumar Saminathan. 2016. subgraph2vec: Learning distributed representations of rooted sub-graphs from large graphs. arXiv preprint arXiv:1606.08928 (2016).Google Scholar
- Ulrich Paquet and Noam Koenigstein. 2013. One-class collaborative filtering with random graphs. In Proceedings of the 22nd international conference on World Wide Web. ACM, 999--1008. Google ScholarDigital Library
- Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. GloVe: Global Vectors for Word Representation. In Empirical Methods in Natural Language Processing (EMNLP). 1532--1543. http://www.aclweb.org/anthology/D14-1162Google Scholar
- Yafeng Ren, Donghong Ji, and Hongbin Zhang. 2014. Positive Unlabeled Learning for Deceptive Reviews Detection. In EMNLP. 488--498.Google Scholar
- N Roy and A McCallum. 2001. Toward optimal active learning through sampling estimation of error reduction. Int. Conf. on Machine Learning. Google ScholarDigital Library
- Noam Shazeer, Ryan Doherty, Colin Evans, and Chris Waterson. 2016. Swivel: Improving embeddings by noticing what's missing. arXiv preprint arXiv:1602.02215 (2016).Google Scholar
- Simon Tong and Daphne Koller. 2001. Support vector machine active learning with applications to text classification. Journal of machine learning research 2, Nov (2001), 45--66. Google ScholarDigital Library
- Trieu H Trinh, Andrew M Dai, Minh-Thang Luong, and Quoc V Le. 2018. Learning longer-term dependencies in rnns with auxiliary losses. arXiv preprint arXiv:1803.00144 (2018).Google Scholar
- Flavian Vasile, Elena Smirnova, and Alexis Conneau. 2016. Meta-prod2vec: Product embeddings using side-information for recommendation. In Proceedings of the 10th ACM Conference on Recommender Systems. ACM, 225--232. Google ScholarDigital Library
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008. Google ScholarDigital Library
- Yazhou Yang and Marco Loog. 2018. A benchmark and comparison of active learning for logistic regression. Pattern Recognition 83 (2018), 401--415.Google ScholarDigital Library
- Zhilin Yang, Zihang Dai, Ruslan Salakhutdinov, and William W Cohen. 2018. Breaking the Softmax Bottleneck: A High-Rank RNN Language Model. In International Conference on Learning Representations (ICLR).Google Scholar
- Kai Yu, Jinbo Bi, and Volker Tresp. 2006. Active learning via transductive experimental design. In Proceedings of the 23rd international conference on Machine learning. ACM, 1081--1088. Google ScholarDigital Library
Index Terms
- Relaxed softmax for PU learning
Recommendations
Reinforced PU-learning with Hybrid Negative Sampling Strategies for Recommendation
The data of recommendation systems typically only contain the purchased item as positive data and other un-purchased items as unlabeled data. To train a good recommendation model, in addition to the known positive information, we also need high-quality ...
Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningLearning from positive and unlabeled data is known as positive-unlabeled (PU) learning in literature and has attracted much attention in recent years. One common approach in PU learning is to sample a set of pseudo-negatives from the unlabeled data ...
DCFGAN: An adversarial deep reinforcement learning framework with improved negative sampling for session-based recommender systems
AbstractIn recent years, with the development of Internet technology, recommender systems have been widely used by virtue of their ability to meet the personalized needs of users. In order to make full use of users’ interactive behaviors, ...
Comments