B. Adhikari, Xinfeng Xu, Naren Ramakrishnan, B. Prakash
Influenza leads to regular losses of lives annually and requires careful monitoring and control by health organizations. Annual influenza forecasts help policymakers implement effective countermeasures to control both seasonal and pandemic outbreaks. Existing forecasting techniques suffer from problems such as poor forecasting performance, lack of modeling flexibility, data sparsity, and/or lack of intepretability. We propose EpiDeep, a novel deep neural network approach for epidemic forecasting which tackles all of these issues by learning meaningful representations of incidence curves in a continuous feature space and accurately predicting future incidences, peak intensity, peak time, and onset of the upcoming season. We present extensive experiments on forecasting ILI (influenza-like illnesses) in the United States, leveraging multiple metrics to quantify success. Our results demonstrate that EpiDeep is successful at learning meaningful embeddings and, more importantly, that these embeddings evolve as the season progresses. Furthermore, our approach outperforms non-trivial baselines by up to 40%.
{"title":"EpiDeep","authors":"B. Adhikari, Xinfeng Xu, Naren Ramakrishnan, B. Prakash","doi":"10.1145/3292500.3330917","DOIUrl":"https://doi.org/10.1145/3292500.3330917","url":null,"abstract":"Influenza leads to regular losses of lives annually and requires careful monitoring and control by health organizations. Annual influenza forecasts help policymakers implement effective countermeasures to control both seasonal and pandemic outbreaks. Existing forecasting techniques suffer from problems such as poor forecasting performance, lack of modeling flexibility, data sparsity, and/or lack of intepretability. We propose EpiDeep, a novel deep neural network approach for epidemic forecasting which tackles all of these issues by learning meaningful representations of incidence curves in a continuous feature space and accurately predicting future incidences, peak intensity, peak time, and onset of the upcoming season. We present extensive experiments on forecasting ILI (influenza-like illnesses) in the United States, leveraging multiple metrics to quantify success. Our results demonstrate that EpiDeep is successful at learning meaningful embeddings and, more importantly, that these embeddings evolve as the season progresses. Furthermore, our approach outperforms non-trivial baselines by up to 40%.","PeriodicalId":186134,"journal":{"name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115665580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traditional recommender systems rely on user feedback such as ratings or clicks to the items, to analyze the user interest and provide personalized recommendations. However, rating or click feedback are limited in that they do not exactly tell why users like or dislike an item. If a user does not like the recommendations and can not effectively express the reasons via rating and clicking, the feedback from the user may be very sparse. These limitations lead to inefficient model learning of the recommender system. To address these limitations, more effective user feedback to the recommendations should be designed, so that the system can effectively understand a user's preference and improve the recommendations over time. In this paper, we propose a novel dialog-based recommender system to interactively recommend a list of items with visual appearance. At each time, the user receives a list of recommended items with visual appearance. The user can point to some items and describe their feedback, such as the desired features in the items they want in natural language. With this natural language based feedback, the recommender system updates and provides another list of items. To model the user behaviors of viewing, commenting and clicking on a list of items, we propose a visual dialog augmented cascade model. To efficiently understand the user preference and learn the model, exploration should be encouraged to provide more diverse recommendations to quickly collect user feedback on more attributes of the items. We propose a variant of the cascading bandits, where the neural representations of the item images and user feedback in natural language are utilized. In a task of recommending a list of footwear, we show that our visual dialog augmented interactive recommender needs around 41.03% rounds of recommendations, compared to the traditional interactive recommender only relying on the user click behavior.
{"title":"A Visual Dialog Augmented Interactive Recommender System","authors":"Tong Yu, Yilin Shen, Hongxia Jin","doi":"10.1145/3292500.3330991","DOIUrl":"https://doi.org/10.1145/3292500.3330991","url":null,"abstract":"Traditional recommender systems rely on user feedback such as ratings or clicks to the items, to analyze the user interest and provide personalized recommendations. However, rating or click feedback are limited in that they do not exactly tell why users like or dislike an item. If a user does not like the recommendations and can not effectively express the reasons via rating and clicking, the feedback from the user may be very sparse. These limitations lead to inefficient model learning of the recommender system. To address these limitations, more effective user feedback to the recommendations should be designed, so that the system can effectively understand a user's preference and improve the recommendations over time. In this paper, we propose a novel dialog-based recommender system to interactively recommend a list of items with visual appearance. At each time, the user receives a list of recommended items with visual appearance. The user can point to some items and describe their feedback, such as the desired features in the items they want in natural language. With this natural language based feedback, the recommender system updates and provides another list of items. To model the user behaviors of viewing, commenting and clicking on a list of items, we propose a visual dialog augmented cascade model. To efficiently understand the user preference and learn the model, exploration should be encouraged to provide more diverse recommendations to quickly collect user feedback on more attributes of the items. We propose a variant of the cascading bandits, where the neural representations of the item images and user feedback in natural language are utilized. In a task of recommending a list of footwear, we show that our visual dialog augmented interactive recommender needs around 41.03% rounds of recommendations, compared to the traditional interactive recommender only relying on the user click behavior.","PeriodicalId":186134,"journal":{"name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121247124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Most current distributed machine learning systems try to scale up model training by using a data-parallel architecture that divides the computation for different samples among workers. We study distributed machine learning from a different motivation, where the information about the same samples, e.g., users and objects, are owned by several parities that wish to collaborate but do not want to share raw data with each other. We propose an asynchronous stochastic gradient descent (SGD) algorithm for such a feature distributed machine learning (FDML) problem, to jointly learn from distributed features, with theoretical convergence guarantees under bounded asynchrony. Our algorithm does not require sharing the original features or even local model parameters between parties, thus preserving the data locality. The system can also easily incorporate differential privacy mechanisms to preserve a higher level of privacy. We implement the FDML system in a parameter server architecture and compare our system with fully centralized learning (which violates data locality) and learning based on only local features, through extensive experiments performed on both a public data set a9a, and a large dataset of 5,000,000 records and 8700 decentralized features from three collaborating apps at Tencent including Tencent MyApp, Tecent QQ Browser and Tencent Mobile Safeguard. Experimental results have demonstrated that the proposed FDML system can be used to significantly enhance app recommendation in Tencent MyApp by leveraging user and item features from other apps, while preserving the locality and privacy of features in each individual app to a high degree.
{"title":"FDML","authors":"Yaochen Hu, Di Niu, Jianming Yang, Shengping Zhou","doi":"10.1145/3292500.3330765","DOIUrl":"https://doi.org/10.1145/3292500.3330765","url":null,"abstract":"Most current distributed machine learning systems try to scale up model training by using a data-parallel architecture that divides the computation for different samples among workers. We study distributed machine learning from a different motivation, where the information about the same samples, e.g., users and objects, are owned by several parities that wish to collaborate but do not want to share raw data with each other. We propose an asynchronous stochastic gradient descent (SGD) algorithm for such a feature distributed machine learning (FDML) problem, to jointly learn from distributed features, with theoretical convergence guarantees under bounded asynchrony. Our algorithm does not require sharing the original features or even local model parameters between parties, thus preserving the data locality. The system can also easily incorporate differential privacy mechanisms to preserve a higher level of privacy. We implement the FDML system in a parameter server architecture and compare our system with fully centralized learning (which violates data locality) and learning based on only local features, through extensive experiments performed on both a public data set a9a, and a large dataset of 5,000,000 records and 8700 decentralized features from three collaborating apps at Tencent including Tencent MyApp, Tecent QQ Browser and Tencent Mobile Safeguard. Experimental results have demonstrated that the proposed FDML system can be used to significantly enhance app recommendation in Tencent MyApp by leveraging user and item features from other apps, while preserving the locality and privacy of features in each individual app to a high degree.","PeriodicalId":186134,"journal":{"name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","volume":"6 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120901263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Scientific computational models are crucial for analyzing and understanding complex real-life systems that are otherwise difficult for experimentation. However, the complex behavior and the vast input-output space of these models often make them opaque, slowing the discovery of novel phenomena. In this work, we present HINT (Hessian INTerestingness) -- a new algorithm that can automatically and systematically explore black-box models and highlight local nonlinear interactions in the input-output space of the model. This tool aims to facilitate the discovery of interesting model behaviors that are unknown to the researchers. Using this simple yet powerful tool, we were able to correctly rank all pairwise interactions in known benchmark models and do so faster and with greater accuracy than state-of-the-art methods. We further applied HINT to existing computational neuroscience models, and were able to reproduce important scientific discoveries that were published years after the creation of those models. Finally, we ran HINT on two real-world models (in neuroscience and earth science) and found new behaviors of the model that were of value to domain experts.
{"title":"Discovering Unexpected Local Nonlinear Interactions in Scientific Black-box Models","authors":"Michael Doron, Idan Segev, Dafna Shahaf","doi":"10.1145/3292500.3330886","DOIUrl":"https://doi.org/10.1145/3292500.3330886","url":null,"abstract":"Scientific computational models are crucial for analyzing and understanding complex real-life systems that are otherwise difficult for experimentation. However, the complex behavior and the vast input-output space of these models often make them opaque, slowing the discovery of novel phenomena. In this work, we present HINT (Hessian INTerestingness) -- a new algorithm that can automatically and systematically explore black-box models and highlight local nonlinear interactions in the input-output space of the model. This tool aims to facilitate the discovery of interesting model behaviors that are unknown to the researchers. Using this simple yet powerful tool, we were able to correctly rank all pairwise interactions in known benchmark models and do so faster and with greater accuracy than state-of-the-art methods. We further applied HINT to existing computational neuroscience models, and were able to reproduce important scientific discoveries that were published years after the creation of those models. Finally, we ran HINT on two real-world models (in neuroscience and earth science) and found new behaviors of the model that were of value to domain experts.","PeriodicalId":186134,"journal":{"name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128765832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In talent recruitment, the job interview aims at selecting the right candidates for the right jobs through assessing their skills and experiences in relation to the job positions. While tremendous efforts have been made in improving job interviews, a long-standing challenge is how to design appropriate interview questions for comprehensively assessing the competencies that may be deemed relevant and representative for person-job fit. To this end, in this research, we focus on the development of a personalized question recommender system, namely DuerQuiz, for enhancing the job interview assessment. DuerQuiz is a fully deployed system, in which a knowledge graph of job skills, Skill-Graph, has been built for comprehensively modeling the relevant competencies that should be assessed in the job interview. Specifically, we first develop a novel skill entity extraction approach based on a bidirectional Long Short-Term Memory (LSTM) with a Conditional Random Field (CRF) layer (LSTM-CRF) neural network enhanced with adapted gate mechanism. In particular, to improve the reliability of extracted skill entities, we design a label propagation method based on more than 10 billion click-through data from the large-scale Baidu query logs. Furthermore, we discover the hypernym-hyponym relations between skill entities and construct the Skill-Graph by leveraging the classifier trained with extensive contextual features. Finally, we design a personalized question recommendation algorithm based on the Skill-Graph for improving the efficiency and effectiveness of job interview assessment. Extensive experiments on real-world recruitment data clearly validate the effectiveness of DuerQuiz, which had been deployed for generating written exercises in the 2018 Baidu campus recruitment event and received remarkable performances in terms of efficiency and effectiveness for selecting outstanding talents compared with a traditional non-personalized human-only assessment approach.
{"title":"DuerQuiz","authors":"Chuan Qin, Hengshu Zhu, Chen Zhu, Tong Xu, Fuzhen Zhuang, Chao Ma, Jingshuai Zhang, Hui Xiong","doi":"10.1145/3292500.3330706","DOIUrl":"https://doi.org/10.1145/3292500.3330706","url":null,"abstract":"In talent recruitment, the job interview aims at selecting the right candidates for the right jobs through assessing their skills and experiences in relation to the job positions. While tremendous efforts have been made in improving job interviews, a long-standing challenge is how to design appropriate interview questions for comprehensively assessing the competencies that may be deemed relevant and representative for person-job fit. To this end, in this research, we focus on the development of a personalized question recommender system, namely DuerQuiz, for enhancing the job interview assessment. DuerQuiz is a fully deployed system, in which a knowledge graph of job skills, Skill-Graph, has been built for comprehensively modeling the relevant competencies that should be assessed in the job interview. Specifically, we first develop a novel skill entity extraction approach based on a bidirectional Long Short-Term Memory (LSTM) with a Conditional Random Field (CRF) layer (LSTM-CRF) neural network enhanced with adapted gate mechanism. In particular, to improve the reliability of extracted skill entities, we design a label propagation method based on more than 10 billion click-through data from the large-scale Baidu query logs. Furthermore, we discover the hypernym-hyponym relations between skill entities and construct the Skill-Graph by leveraging the classifier trained with extensive contextual features. Finally, we design a personalized question recommendation algorithm based on the Skill-Graph for improving the efficiency and effectiveness of job interview assessment. Extensive experiments on real-world recruitment data clearly validate the effectiveness of DuerQuiz, which had been deployed for generating written exercises in the 2018 Baidu campus recruitment event and received remarkable performances in terms of efficiency and effectiveness for selecting outstanding talents compared with a traditional non-personalized human-only assessment approach.","PeriodicalId":186134,"journal":{"name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129257474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Daizong Ding, Mi Zhang, Xudong Pan, Min Yang, Xiangnan He
Time series prediction is an intensively studied topic in data mining. In spite of the considerable improvements, recent deep learning-based methods overlook the existence of extreme events, which result in weak performance when applying them to real time series. Extreme events are rare and random, but do play a critical role in many real applications, such as the forecasting of financial crisis and natural disasters. In this paper, we explore the central theme of improving the ability of deep learning on modeling extreme events for time series prediction. Through the lens of formal analysis, we first find that the weakness of deep learning methods roots in the conventional form of quadratic loss. To address this issue, we take inspirations from the Extreme Value Theory, developing a new form of loss called Extreme Value Loss (EVL) for detecting the future occurrence of extreme events. Furthermore, we propose to employ Memory Network in order to memorize extreme events in historical records.By incorporating EVL with an adapted memory network module, we achieve an end-to-end framework for time series prediction with extreme events. Through extensive experiments on synthetic data and two real datasets of stock and climate, we empirically validate the effectiveness of our framework. Besides, we also provide a proper choice for hyper-parameters in our proposed framework by conducting several additional experiments.
{"title":"Modeling Extreme Events in Time Series Prediction","authors":"Daizong Ding, Mi Zhang, Xudong Pan, Min Yang, Xiangnan He","doi":"10.1145/3292500.3330896","DOIUrl":"https://doi.org/10.1145/3292500.3330896","url":null,"abstract":"Time series prediction is an intensively studied topic in data mining. In spite of the considerable improvements, recent deep learning-based methods overlook the existence of extreme events, which result in weak performance when applying them to real time series. Extreme events are rare and random, but do play a critical role in many real applications, such as the forecasting of financial crisis and natural disasters. In this paper, we explore the central theme of improving the ability of deep learning on modeling extreme events for time series prediction. Through the lens of formal analysis, we first find that the weakness of deep learning methods roots in the conventional form of quadratic loss. To address this issue, we take inspirations from the Extreme Value Theory, developing a new form of loss called Extreme Value Loss (EVL) for detecting the future occurrence of extreme events. Furthermore, we propose to employ Memory Network in order to memorize extreme events in historical records.By incorporating EVL with an adapted memory network module, we achieve an end-to-end framework for time series prediction with extreme events. Through extensive experiments on synthetic data and two real datasets of stock and climate, we empirically validate the effectiveness of our framework. Besides, we also provide a proper choice for hyper-parameters in our proposed framework by conducting several additional experiments.","PeriodicalId":186134,"journal":{"name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130235691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rui Yan, Ran Le, Yang Song, Tao Zhang, Xiangliang Zhang, Dongyan Zhao
Online recruitment services are now rapidly changing the landscape of hiring traditions on the job market. There are hundreds of millions of registered users with resumes, and tens of millions of job postings available on the Web. Learning good job-resume matching for recruitment services is important. Existing studies on job-resume matching generally focus on learning good representations of job descriptions and resume texts with comprehensive matching structures. We assume that it would bring benefits to learn the preference of both recruiters and job-seekers from previous interview histories and expect such preference is helpful to improve job-resume matching. To this end, in this paper, we propose a novel matching network with preference modeled. The key idea is to explore the latent preference given the history of all interviewed candidates for a job posting and the history of all job applications for a particular talent. To be more specific, we propose a profiling memory module to learn the latent preference representation by interacting with both the job and resume sides. We then incorporate the preference into the matching framework as an end-to-end learnable neural network. Based on the real-world data from an online recruitment platform namely "Boss Zhipin", the experimental results show that the proposed model could improve the job-resume matching performance against a series of state-of-the-art methods. In this way, we demonstrate that recruiters and talents indeed have preference and such preference can improve job-resume matching on the job market.
{"title":"Interview Choice Reveals Your Preference on the Market: To Improve Job-Resume Matching through Profiling Memories","authors":"Rui Yan, Ran Le, Yang Song, Tao Zhang, Xiangliang Zhang, Dongyan Zhao","doi":"10.1145/3292500.3330963","DOIUrl":"https://doi.org/10.1145/3292500.3330963","url":null,"abstract":"Online recruitment services are now rapidly changing the landscape of hiring traditions on the job market. There are hundreds of millions of registered users with resumes, and tens of millions of job postings available on the Web. Learning good job-resume matching for recruitment services is important. Existing studies on job-resume matching generally focus on learning good representations of job descriptions and resume texts with comprehensive matching structures. We assume that it would bring benefits to learn the preference of both recruiters and job-seekers from previous interview histories and expect such preference is helpful to improve job-resume matching. To this end, in this paper, we propose a novel matching network with preference modeled. The key idea is to explore the latent preference given the history of all interviewed candidates for a job posting and the history of all job applications for a particular talent. To be more specific, we propose a profiling memory module to learn the latent preference representation by interacting with both the job and resume sides. We then incorporate the preference into the matching framework as an end-to-end learnable neural network. Based on the real-world data from an online recruitment platform namely \"Boss Zhipin\", the experimental results show that the proposed model could improve the job-resume matching performance against a series of state-of-the-art methods. In this way, we demonstrate that recruiters and talents indeed have preference and such preference can improve job-resume matching on the job market.","PeriodicalId":186134,"journal":{"name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127773673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Relation extraction in knowledge base construction has been researched for the last decades due to its applicability to many problems. Most classical works, such as supervised information extraction and distant supervision, focus on how to construct the knowledge base (KB) by utilizing the large number of labels or certain related KBs. However, in many real-world scenarios, the existing methods may not perform well when a new knowledge base is required but only scarce labels or few related KBs available. In this paper, we propose a novel approach called, Relation Extraction via Domain-aware Transfer Learning (ReTrans), to extract relation mentions from a given text corpus by exploring the experience from a large amount of existing KBs which may not be closely related to the target relation. We first propose to initialize the representation of relation mentions from the massive text corpus and update those representations according to existing KBs. Based on the representations of relation mentions, we investigate the contribution of each KB to the target task and propose to select useful KBs for boosting the effectiveness of the proposed approach. Based on selected KBs, we develop a novel domain-aware transfer learning framework to transfer knowledge from source domains to the target domain, aiming to infer the true relation mentions in the unstructured text corpus. Most importantly, we give the stability and generalization bound of ReTrans. Experimental results on the real world datasets well demonstrate that the effectiveness of our approach, which outperforms all the state-of-the-art baselines.
{"title":"Relation Extraction via Domain-aware Transfer Learning","authors":"Shimin Di, Yanyan Shen, Lei Chen","doi":"10.1145/3292500.3330890","DOIUrl":"https://doi.org/10.1145/3292500.3330890","url":null,"abstract":"Relation extraction in knowledge base construction has been researched for the last decades due to its applicability to many problems. Most classical works, such as supervised information extraction and distant supervision, focus on how to construct the knowledge base (KB) by utilizing the large number of labels or certain related KBs. However, in many real-world scenarios, the existing methods may not perform well when a new knowledge base is required but only scarce labels or few related KBs available. In this paper, we propose a novel approach called, Relation Extraction via Domain-aware Transfer Learning (ReTrans), to extract relation mentions from a given text corpus by exploring the experience from a large amount of existing KBs which may not be closely related to the target relation. We first propose to initialize the representation of relation mentions from the massive text corpus and update those representations according to existing KBs. Based on the representations of relation mentions, we investigate the contribution of each KB to the target task and propose to select useful KBs for boosting the effectiveness of the proposed approach. Based on selected KBs, we develop a novel domain-aware transfer learning framework to transfer knowledge from source domains to the target domain, aiming to infer the true relation mentions in the unstructured text corpus. Most importantly, we give the stability and generalization bound of ReTrans. Experimental results on the real world datasets well demonstrate that the effectiveness of our approach, which outperforms all the state-of-the-art baselines.","PeriodicalId":186134,"journal":{"name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127146003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lucas Bernardi, Themistoklis Mavridis, PabloA . Estevez
Booking.com is the world's largest online travel agent where millions of guests find their accommodation and millions of accommodation providers list their properties including hotels, apartments, bed and breakfasts, guest houses, and more. During the last years we have applied Machine Learning to improve the experience of our customers and our business. While most of the Machine Learning literature focuses on the algorithmic or mathematical aspects of the field, not much has been published about how Machine Learning can deliver meaningful impact in an industrial environment where commercial gains are paramount. We conducted an analysis on about 150 successful customer facing applications of Machine Learning, developed by dozens of teams in Booking.com, exposed to hundreds of millions of users worldwide and validated through rigorous Randomized Controlled Trials. Following the phases of a Machine Learning project we describe our approach, the many challenges we found, and the lessons we learned while scaling up such a complex technology across our organization. Our main conclusion is that an iterative, hypothesis driven process, integrated with other disciplines was fundamental to build 150 successful products enabled by Machine Learning.
{"title":"150 Successful Machine Learning Models: 6 Lessons Learned at Booking.com","authors":"Lucas Bernardi, Themistoklis Mavridis, PabloA . Estevez","doi":"10.1145/3292500.3330744","DOIUrl":"https://doi.org/10.1145/3292500.3330744","url":null,"abstract":"Booking.com is the world's largest online travel agent where millions of guests find their accommodation and millions of accommodation providers list their properties including hotels, apartments, bed and breakfasts, guest houses, and more. During the last years we have applied Machine Learning to improve the experience of our customers and our business. While most of the Machine Learning literature focuses on the algorithmic or mathematical aspects of the field, not much has been published about how Machine Learning can deliver meaningful impact in an industrial environment where commercial gains are paramount. We conducted an analysis on about 150 successful customer facing applications of Machine Learning, developed by dozens of teams in Booking.com, exposed to hundreds of millions of users worldwide and validated through rigorous Randomized Controlled Trials. Following the phases of a Machine Learning project we describe our approach, the many challenges we found, and the lessons we learned while scaling up such a complex technology across our organization. Our main conclusion is that an iterative, hypothesis driven process, integrated with other disciplines was fundamental to build 150 successful products enabled by Machine Learning.","PeriodicalId":186134,"journal":{"name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","volume":"10 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126034289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Eitam Sheetrit, N. Nissim, D. Klimov, Yuval Shahar
Sepsis is a condition caused by the body's overwhelming and life-threatening response to infection, which can lead to tissue damage, organ failure, and finally death. Today, sepsis is one of the leading causes of mortality among populations in intensive care units (ICUs). Sepsis is difficult to predict, diagnose, and treat, as it involves analyzing different sets of multivariate time-series, usually with problems of missing data, different sampling frequencies, and random noise. Here, we propose a new dynamic-behavior-based model, which we call a Temporal Probabilistic proFile (TPF), for classification and prediction tasks of multivariate time series. In the TPF method, the raw, time-stamped data are first abstracted into a series of higher-level, meaningful concepts, which hold over intervals characterizing time periods. We then discover frequently repeating temporal patterns within the data. Using the discovered patterns, we create a probabilistic distribution of the temporal patterns of the overall entity population, of each target class in it, and of each entity. We then exploit TPFs as meta-features to classify the time series of new entities, or to predict their outcome, by measuring their TPF distance, either to the aggregated TPF of each class, or to the individual TPFs of each of the entities, using negative cross entropy. Our experimental results on a large benchmark clinical data set show that TPFs improve sepsis prediction capabilities, and perform better than other machine learning approaches.
{"title":"Temporal Probabilistic Profiles for Sepsis Prediction in the ICU","authors":"Eitam Sheetrit, N. Nissim, D. Klimov, Yuval Shahar","doi":"10.1145/3292500.3330747","DOIUrl":"https://doi.org/10.1145/3292500.3330747","url":null,"abstract":"Sepsis is a condition caused by the body's overwhelming and life-threatening response to infection, which can lead to tissue damage, organ failure, and finally death. Today, sepsis is one of the leading causes of mortality among populations in intensive care units (ICUs). Sepsis is difficult to predict, diagnose, and treat, as it involves analyzing different sets of multivariate time-series, usually with problems of missing data, different sampling frequencies, and random noise. Here, we propose a new dynamic-behavior-based model, which we call a Temporal Probabilistic proFile (TPF), for classification and prediction tasks of multivariate time series. In the TPF method, the raw, time-stamped data are first abstracted into a series of higher-level, meaningful concepts, which hold over intervals characterizing time periods. We then discover frequently repeating temporal patterns within the data. Using the discovered patterns, we create a probabilistic distribution of the temporal patterns of the overall entity population, of each target class in it, and of each entity. We then exploit TPFs as meta-features to classify the time series of new entities, or to predict their outcome, by measuring their TPF distance, either to the aggregated TPF of each class, or to the individual TPFs of each of the entities, using negative cross entropy. Our experimental results on a large benchmark clinical data set show that TPFs improve sepsis prediction capabilities, and perform better than other machine learning approaches.","PeriodicalId":186134,"journal":{"name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114084858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：