Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining最新文献_第9页

Generalized Zero-Shot Extreme Multi-label Learning 广义零射击极限多标签学习

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining Pub Date : 2021-08-14 DOI: 10.1145/3447548.3467426

Nilesh Gupta, Sakina Bohra, Yashoteja Prabhu, Saurabh.S. Purohit, M. Varma

{"title":"Generalized Zero-Shot Extreme Multi-label Learning","authors":"Nilesh Gupta, Sakina Bohra, Yashoteja Prabhu, Saurabh.S. Purohit, M. Varma","doi":"10.1145/3447548.3467426","DOIUrl":"https://doi.org/10.1145/3447548.3467426","url":null,"abstract":"Extreme Multi-label Learning (XML) involves assigning the subset of most relevant labels to a data point from millions of label choices. A hitherto unaddressed challenge in XML is that of predicting unseen labels with no training points. These form a significant fraction of total labels and contain fresh and personalized information desired by end users. Most existing extreme classifiers are not equipped for zero-shot label prediction and hence fail to leverage unseen labels. As a remedy, this paper proposes a novel approach called ZestXML for the task of Generalized Zero-shot XML (GZXML) where relevant labels have to be chosen from all available seen and unseen labels. ZestXML learns to project a data point's features close to the features of its relevant labels through a highly sparsified linear transform. This L0-constrained linear map between the two high-dimensional feature vectors is tractably recovered through a novel optimizer based on Hard Thresholding. By effectively leveraging the sparsities in features, labels and the learnt model, ZestXML achieves higher accuracy and smaller model size than existing XML approaches while also promoting efficient training & prediction, real-time label update as well as explainable prediction. Experiments on large-scale GZXML datasets demonstrated that ZestXML can be up to 14% and 10% more accurate than state-of-the-art extreme classifiers and leading BERT-based dense retrievers respectively, while having 10x smaller model size. ZestXML trains on largest dataset with 31M labels in just 30 hours on a single core of a commodity desktop. When added to an large ensemble of existing models in Bing Sponsored Search Advertising, ZestXML significantly improved click yield of IR based system by 17% and unseen query coverage by 3.4% respectively. ZestXML's source code and benchmark datasets for GZXML will be publically released for research purposes here.","PeriodicalId":421090,"journal":{"name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128682478","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}

引用次数: 22

RAPT: Pre-training of Time-Aware Transformer for Learning Robust Healthcare Representation RAPT:用于学习稳健医疗保健表示的时间感知转换器的预训练

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining Pub Date : 2021-08-14 DOI: 10.1145/3447548.3467069

Houxing Ren, Jingyuan Wang, Wayne Xin Zhao, Ning Wu

{"title":"RAPT: Pre-training of Time-Aware Transformer for Learning Robust Healthcare Representation","authors":"Houxing Ren, Jingyuan Wang, Wayne Xin Zhao, Ning Wu","doi":"10.1145/3447548.3467069","DOIUrl":"https://doi.org/10.1145/3447548.3467069","url":null,"abstract":"With the development of electronic health records (EHRs), prenatal care examination records have become available for developing automatic prediction or diagnosis approaches with machine learning methods. In this paper, we study how to effectively learn representations applied to various downstream tasks for EHR data. Although several methods have been proposed in this direction, they usually adapt classic sequential models to solve one specific diagnosis task or address unique EHR data issues. This makes it difficult to reuse these existing methods for the early diagnosis of pregnancy complications or provide a general solution to address the series of health problems caused by pregnancy complications. In this paper, we propose a novel model RAPT, which stands for RepresentAtion by Pre-training time-aware Transformer. To associate pre-training and EHR data, we design an architecture that is suitable for both modeling EHR data and pre-training, namely time-aware Transformer. To handle various characteristics in EHR data, such as insufficiency, we carefully devise three pre-training tasks to handle data insufficiency, data incompleteness and short sequence problems, namely similarity prediction, masked prediction and reasonability check. In this way, our representations can capture various EHR data characteristics. Extensive experimental results for four downstream tasks have shown the effectiveness of the proposed approach. We also introduce sensitivity analysis to interpret the model and design an interface to show results and interpretation for doctors. Finally, we implement a diagnosis system for pregnancy complications based on our pre-training model. Doctors and pregnant women can benefit from the diagnosis system in early diagnosis of pregnancy complications.","PeriodicalId":421090,"journal":{"name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126207091","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}

引用次数: 19

Que2Search: Fast and Accurate Query and Document Understanding for Search at Facebook Que2Search:快速和准确的查询和文档理解搜索在Facebook

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining Pub Date : 2021-08-14 DOI: 10.1145/3447548.3467127

Yiqun Liu, Kaushik Rangadurai, Yunzhong He, Siddarth Malreddy, Xunlong Gui, Xiaoyi Liu, Fedor Borisyuk

{"title":"Que2Search: Fast and Accurate Query and Document Understanding for Search at Facebook","authors":"Yiqun Liu, Kaushik Rangadurai, Yunzhong He, Siddarth Malreddy, Xunlong Gui, Xiaoyi Liu, Fedor Borisyuk","doi":"10.1145/3447548.3467127","DOIUrl":"https://doi.org/10.1145/3447548.3467127","url":null,"abstract":"In this paper, we present Que2Search, a deployed query and product understanding system for search. Que2Search leverages multi-task and multi-modal learning approaches to train query and product representations. We achieve over 5% absolute offline relevance improvement and over 4% online engagement gain over state-of-the-art Facebook product understanding system by combining the latest multilingual natural language understanding architectures like XLM and XLM-R with multi-modal fusion techniques. In this paper, we describe how we deploy XLM-based search query understanding model that runs <1.5ms @P99 on CPU at Facebook scale, which has been a significant challenge in the industry. We also describe what model optimizations worked (and what did not) based on numerous offline and online A/B experiments. We deploy Que2Search to Facebook Marketplace Search and share our deployment experience to production and tuning tricks to achieve higher efficiency in online A/B experiments. Que2Search has demonstrated gains in production applications and operates at Facebook scale.","PeriodicalId":421090,"journal":{"name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127776816","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}

引用次数: 22

Environment Agnostic Invariant Risk Minimization for Classification of Sequential Datasets 序列数据集分类的环境不可知不变风险最小化

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining Pub Date : 2021-08-14 DOI: 10.1145/3447548.3467324

Praveen Venkateswaran, Vinod Muthusamy, Vatche Isahagian, N. Venkatasubramanian

{"title":"Environment Agnostic Invariant Risk Minimization for Classification of Sequential Datasets","authors":"Praveen Venkateswaran, Vinod Muthusamy, Vatche Isahagian, N. Venkatasubramanian","doi":"10.1145/3447548.3467324","DOIUrl":"https://doi.org/10.1145/3447548.3467324","url":null,"abstract":"The generalization of predictive models that follow the standard risk minimization paradigm of machine learning can be hindered by the presence of spurious correlations in the data. Identifying invariant predictors while training on data from multiple environments can influence models to focus on features that have an invariant causal relationship with the target, while reducing the effect of spurious features. Such invariant risk minimization approaches heavily rely on clearly defined environments and data being perfectly segmented into these environments for training. However, in real-world settings, perfect segmentation is challenging to achieve and these environment-aware approaches prove to be sensitive to segmentation errors. In this work, we present an environment-agnostic approach to develop generalizable models for classification tasks in sequential datasets without needing prior knowledge of environments. We show that our approach results in models that can generalize to out-of-distribution data and are not influenced by spurious correlations. We evaluate our approach on real-world sequential datasets from various domains.","PeriodicalId":421090,"journal":{"name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127467105","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}

引用次数: 10

Dialogue Based Disease Screening Through Domain Customized Reinforcement Learning 基于对话的疾病筛选，通过领域定制强化学习

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining Pub Date : 2021-08-14 DOI: 10.1145/3447548.3467255

Zhuo Liu, Yanxuan Li, Xingzhi Sun, Fei Wang, Gang Hu, G. Xie

{"title":"Dialogue Based Disease Screening Through Domain Customized Reinforcement Learning","authors":"Zhuo Liu, Yanxuan Li, Xingzhi Sun, Fei Wang, Gang Hu, G. Xie","doi":"10.1145/3447548.3467255","DOIUrl":"https://doi.org/10.1145/3447548.3467255","url":null,"abstract":"In this paper, we study the problem of leveraging dialogue agents learned from reinforcement learning (RL) that can interact with patients for automatic disease screening. This application requires efficient and effective inquiry of appropriate symptoms to make accurate diagnosis recommendations. Existing studies have tried to use RL to perform both symptom inquiry and diagnosis simultaneously, which needs to deal with a large, heterogeneous action space that affects the learning efficiency and effectiveness. To address the challenge, we propose to leverage the models learned from the dialogue data to customize the settings of the reinforcement learning for more efficient action space exploration. In particular, a supervised diagnosis model is built and involved in the definition of state and reward. We also develop the clustering method to form a hierarchy in the action space. These customizations can make the learning task focus on checking the most relevant symptoms, which effectively boost the confidence of diagnosis. Besides, a novel hierarchical reinforcement learning framework with the pretraining strategy is used to reduce the dimension of action space and help the model to converge. For empirical evaluations, we conduct extensive experiments on both synthetic and real-world datasets. The results have demonstrated the superiority of our approach in diagnostic accuracy and interaction efficiency compared with other baseline methods.","PeriodicalId":421090,"journal":{"name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127333297","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}

引用次数: 3

An Efficient and Scalable Algorithm for Estimating Kemeny's Constant of a Markov Chain on Large Graphs 大型图上马尔可夫链Kemeny常数估计的一种高效可扩展算法

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining Pub Date : 2021-08-14 DOI: 10.1145/3447548.3467431

Shiju Li, Xin Huang, Chul-Ho Lee

{"title":"An Efficient and Scalable Algorithm for Estimating Kemeny's Constant of a Markov Chain on Large Graphs","authors":"Shiju Li, Xin Huang, Chul-Ho Lee","doi":"10.1145/3447548.3467431","DOIUrl":"https://doi.org/10.1145/3447548.3467431","url":null,"abstract":"The mean hitting time of a Markov chain on a graph from an arbitrary node to a target node randomly chosen according to its stationary distribution is called Kemeny's constant, which is an important metric for network analysis and has a wide range of applications. It is, however, still computationally expensive to evaluate the Kemeny's constant, especially when it comes to a large graph, since it requires the computation of the spectrum of the corresponding transition matrix or its normalized Laplacian matrix. In this paper, we propose a simple yet computationally efficient Monte Carlo algorithm to approximate the Kemeny's constant, which is equipped with an ε,δ)-approximation estimator. Thanks to its inherent algorithmic parallelism, we are able to develop its parallel implementation on a GPU to speed up the computation. We provide extensive experiment results on 13 real-world graphs to demonstrate the computational efficiency and scalability of our algorithm, which achieves up to 500x speed-up over the state-of-the-art algorithm. We further present its practical enhancements to make our algorithm ready for practical use in real-world settings.","PeriodicalId":421090,"journal":{"name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132276398","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}

引用次数: 2

Online Additive Quantization 在线加性量化

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining Pub Date : 2021-08-14 DOI: 10.1145/3447548.3467441

Qi Liu, Jin Zhang, Defu Lian, Yong Ge, Jianhui Ma, Enhong Chen

引用次数: 5

A Visual Tour of Bias Mitigation Techniques for Word Representations 单词表示的偏见缓解技术视觉之旅

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining Pub Date : 2021-08-14 DOI: 10.1145/3447548.3470807

Archit Rathore, Sunipa Dev, J. M. Phillips, Vivek Srikumar, Bei Wang

引用次数: 2

Interactive Audience Expansion On Large Scale Online Visitor Data 基于大规模在线访问者数据的互动受众扩展

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining Pub Date : 2021-08-14 DOI: 10.1145/3447548.3467179

G. Chan, Tung Mai, Anup B. Rao, Ryan A. Rossi, F. Du, Cláudio T. Silva, J. Freire

{"title":"Interactive Audience Expansion On Large Scale Online Visitor Data","authors":"G. Chan, Tung Mai, Anup B. Rao, Ryan A. Rossi, F. Du, Cláudio T. Silva, J. Freire","doi":"10.1145/3447548.3467179","DOIUrl":"https://doi.org/10.1145/3447548.3467179","url":null,"abstract":"Online marketing platforms often store millions of website visitors' behavior as a large sparse matrix with rows as visitors and columns as behavior. These platforms allow marketers to conduct Audience Expansion, a technique to identify new audiences with similar behavior to the original target audiences. In this paper, we propose a method to achieve interactive Audience Expansion from millions of visitor data efficiently. Unlike other methods that undergo significant computations upon inputs, our approach provides interactive responses when a marketer inputs the target audiences and similarity measures. The idea is to apply data summarization technique on the large visitor matrix to obtain a small set of summaries representing the similarities in the matrix. We propose efficient algorithms to compute the data summaries on a distributed computing environment (i.e., Spark) and conduct the expansion using the summaries. Our experiment shows that our approach (1) provides 10 times more accurate and 27 times faster Audience Expansion results on real datasets and (2) achieves a 98% speed-up compared to straightforward data summarization implementations. We also present an interface to apply the algorithm for real-world scenarios.","PeriodicalId":421090,"journal":{"name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117217685","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}

引用次数: 2

Robust Object Detection Fusion Against Deception 抗欺骗鲁棒目标检测融合

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining Pub Date : 2021-08-14 DOI: 10.1145/3447548.3467121

Ka-Ho Chow

{"title":"Robust Object Detection Fusion Against Deception","authors":"Ka-Ho Chow","doi":"10.1145/3447548.3467121","DOIUrl":"https://doi.org/10.1145/3447548.3467121","url":null,"abstract":"Deep neural network (DNN) based object detection has become an integral part of numerous cyber-physical systems, perceiving physical environments and responding proactively to real-time events. Recent studies reveal that well-trained multi-task learners like DNN-based object detectors perform poorly in the presence of deception. This paper presents FUSE, a deception-resilient detection fusion approach with three novel contributions. First, we develop diversity-enhanced fusion teaming mechanisms, including diversity-enhanced joint training algorithms, for producing high diversity fusion detectors. Second, we introduce a three-tier detection fusion framework and a graph partitioning algorithm to construct fusion-verified detection outputs through three mutually reinforcing components: objectness fusion, bounding box fusion, and classification fusion. Third but not least, we provide a formal analysis of robustness enhancement by FUSE-protected systems. Extensive experiments are conducted on eleven detectors from three families of detection algorithms on two benchmark datasets. We show that FUSE guarantees strong robustness in mitigating the state-of-the-art deception attacks, including adversarial patches - a form of physical attacks using confined visual distortion.","PeriodicalId":421090,"journal":{"name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132749542","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}

引用次数: 4