Filters








6 Hits in 2.6 sec

Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimation [article]

Siyuan Guo, Lixin Zou, Yiding Liu, Wenwen Ye, Suqi Cheng, Shuaiqiang Wang, Hechang Chen, Dawei Yin, Yi Chang
2021 pre-print
Post-click conversion, as a strong signal indicating the user preference, is salutary for building recommender systems.  ...  However, accurately estimating the post-click conversion rate (CVR) is challenging due to the selection bias, i.e., the observed clicked events usually happen on users' preferred items.  ...  To address the above-mentioned challenges, we propose the enhanced doubly robust learning approach for debiasing post-click conversion rate estimation.  ... 
doi:10.1145/3404835.3462917 arXiv:2105.13623v1 fatcat:kjq7fxecz5hq5pkyy4q4ljlfwq

Measuring Average Treatment Effect from Heavy-tailed Data [article]

Jason Wang, Pauline Burke
2019 arXiv   pre-print
While we may have samples large enough for Central Limit Theorem to kick in, experimentation is challenging due to the wide confidence interval of estimation.  ...  In particular, the legitimacy of false positive rate could be at risk.  ...  ACKNOWLEDGMENTS David Goldberg helped a lot when he was with eBay, especially in the design of winsorization. e authors would also thank rest of eBay Experimentation Science team for their suggestions.  ... 
arXiv:1905.09252v1 fatcat:q46wa5m5zbb6bhppp2tw34374i

Bias and Debias in Recommender System: A Survey and Future Directions [article]

Jiawei Chen, Hande Dong, Xiang Wang, Fuli Feng, Meng Wang, Xiangnan He
2021 arXiv   pre-print
The summary of debiasing methods reviewed in this survey can be found at .  ...  While recent years have witnessed a rapid growth of research papers on recommender system (RS), most of the papers focus on inventing machine learning models to better fit user behavior data.  ...  Knowledge graph would be a powerful tool for developing a feature-enhanced general debiasing framework.  ... 
arXiv:2010.03240v2 fatcat:6fticc3otndsra2whs5e4nrdpi

Implementation of Fog computing for reliable E-health applications

Razvan Craciunescu, Albena Mihovska, Mihail Mihaylov, Sofoklis Kyriazakos, Ramjee Prasad, Simona Halunga
2015 2015 49th Asilomar Conference on Signals, Systems and Computers  
Finally, we will provide 'structured' CS algorithms for the joint estimation scheme and evaluate its performance.  ...  An important aspect is robust and resource efficient preamble design to minimize missed detection and false alarm probabilities of service requests.  ...  This estimator has greatly improved robustness over the conventional estimator when coherence is low.  ... 
doi:10.1109/acssc.2015.7421170 dblp:conf/acssc/CraciunescuMMKP15 fatcat:qm6mki5z6bcvrfimkmqjyrxaxm

Ping-pong beam training for reciprocal channels with delay spread

Elisabeth de Carvalho, Jorgen Bach Andersen
2015 2015 49th Asilomar Conference on Signals, Systems and Computers  
Finally, we will provide 'structured' CS algorithms for the joint estimation scheme and evaluate its performance.  ...  Massive Machine Type Communication characterized by low data-rates and low activity devices requires new physical layer solutions.  ...  This estimator has greatly improved robustness over the conventional estimator when coherence is low.  ... 
doi:10.1109/acssc.2015.7421451 dblp:conf/acssc/CarvalhoA15 fatcat:mqokuvnh3zg45licnfbgxyvxfu

An Impossible Dialogue! Nominal Utterances and Populist Rhetoric in an Italian Twitter Corpus of Hate Speech against Immigrants

Gloria Comandini, Viviana Patti
2019 Proceedings of the Third Workshop on Abusive Language Online   unpublished
Thus, human ratings in the context of toxicity in language raise important questions around the various socio-cultural biases that affect those ratings, but also on the impact it has on the psychological  ...  In order to situate our conversation around this theme, we have confirmed four keynote speakers and panelists who are leading experts on content moderation, crowd work, and the impact of algorithmic solutions  ...  Conclusion and Future Work We reported our results on several obvious stateof-the-art deep learning architectures and reported better results on Capsule network.  ... 
doi:10.18653/v1/w19-3518 fatcat:liwo47b4kzblhifxy7gn4lrifq