The research of geoscience plays a strong role in helping people gain a better understanding of the Earth. To effectively represent the knowledge (KG) from enormous geoscience research papers, knowledge graphs can be a powerful means. In the face of enormous geoscience research papers, knowledge graphs can be a powerful means to manage the relationships of data and integrate knowledge extracted from them. However, the existing geoscience KGs mainly focus on the external connection between concepts, whereas the potential abundant information contained in the internal multimodal data of the paper is largely overlooked for more fine-grained knowledge mining. To this end, we propose GAKG, a large-scale multimodal academic KG based on 1.12 million papers published in various geoscience-related journals. In addition to the bibliometrics elements, we also extracted the internal illustrations, tables, and text information of the articles, and dig out the knowledge entities of the papers and the era and spatial attributes of the articles, coupling multimodal academic data and features. Specifically, GAKG realizes knowledge entity extraction under our proposed Human-In-the-Loop framework, the novelty of which is to combine the techniques of machine reading and information retrieval with manual annotation of geoscientists in the loop. Considering the fact that literature of geoscience often contains more abundant illustrations and time scale information compared with that of other disciplines, we extract all the geographical information and era from the geoscience papers' text and illustrations, mapping papers to the atlas and chronology. Based on GAKG, we build several knowledge discovery benchmarks for finding geoscience communities and predicting potential links. GAKG and its services have been made publicly available and user-friendly.
{"title":"GAKG: A Multimodal Geoscience Academic Knowledge Graph","authors":"Cheng Deng, Yuting Jia, Hui Xu, Chong Zhang, Jingyao Tang, Luoyi Fu, Weinan Zhang, Haisong Zhang, Xinbing Wang, Cheng Zhou","doi":"10.1145/3459637.3482003","DOIUrl":"https://doi.org/10.1145/3459637.3482003","url":null,"abstract":"The research of geoscience plays a strong role in helping people gain a better understanding of the Earth. To effectively represent the knowledge (KG) from enormous geoscience research papers, knowledge graphs can be a powerful means. In the face of enormous geoscience research papers, knowledge graphs can be a powerful means to manage the relationships of data and integrate knowledge extracted from them. However, the existing geoscience KGs mainly focus on the external connection between concepts, whereas the potential abundant information contained in the internal multimodal data of the paper is largely overlooked for more fine-grained knowledge mining. To this end, we propose GAKG, a large-scale multimodal academic KG based on 1.12 million papers published in various geoscience-related journals. In addition to the bibliometrics elements, we also extracted the internal illustrations, tables, and text information of the articles, and dig out the knowledge entities of the papers and the era and spatial attributes of the articles, coupling multimodal academic data and features. Specifically, GAKG realizes knowledge entity extraction under our proposed Human-In-the-Loop framework, the novelty of which is to combine the techniques of machine reading and information retrieval with manual annotation of geoscientists in the loop. Considering the fact that literature of geoscience often contains more abundant illustrations and time scale information compared with that of other disciplines, we extract all the geographical information and era from the geoscience papers' text and illustrations, mapping papers to the atlas and chronology. Based on GAKG, we build several knowledge discovery benchmarks for finding geoscience communities and predicting potential links. GAKG and its services have been made publicly available and user-friendly.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131480914","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}
Recently, an early exit network, which dynamically adjusts the model complexity during inference time, has achieved remarkable performance and neural network efficiency to be used for various applications. So far, many researchers have been focusing on reducing the redundancy of input sample or model architecture. However, they were unsuccessful at resolving the performance drop of early classifiers that make predictions with insufficient high-level feature information. Consequently, the performance degradation of early classifiers had a devastating effect on the entire network performance sharing the backbone. Thus, in this paper, we propose an Efficient Multi-Scale Feature Generation Adaptive Network (EMGNet), which not only reduced the redundancy of the architecture but also generates multi-scale features to improve the performance of the early exit network. Our approach renders multi-scale feature generation highly efficient through sharing weights in the center of the convolution kernel. Also, our gating network effectively learns to automatically determine the proper multi-scale feature ratio required for each convolution layer in different locations of the network. We demonstrate that our proposed model outperforms the state-of-the-art adaptive networks on CIFAR10, CIFAR100, and ImageNet datasets. The implementation code is available at https://github.com/lee-gwang/EMGNet
{"title":"Efficient Multi-Scale Feature Generation Adaptive Network","authors":"Gwanghan Lee, Minhan Kim, Simon S. Woo","doi":"10.1145/3459637.3482337","DOIUrl":"https://doi.org/10.1145/3459637.3482337","url":null,"abstract":"Recently, an early exit network, which dynamically adjusts the model complexity during inference time, has achieved remarkable performance and neural network efficiency to be used for various applications. So far, many researchers have been focusing on reducing the redundancy of input sample or model architecture. However, they were unsuccessful at resolving the performance drop of early classifiers that make predictions with insufficient high-level feature information. Consequently, the performance degradation of early classifiers had a devastating effect on the entire network performance sharing the backbone. Thus, in this paper, we propose an Efficient Multi-Scale Feature Generation Adaptive Network (EMGNet), which not only reduced the redundancy of the architecture but also generates multi-scale features to improve the performance of the early exit network. Our approach renders multi-scale feature generation highly efficient through sharing weights in the center of the convolution kernel. Also, our gating network effectively learns to automatically determine the proper multi-scale feature ratio required for each convolution layer in different locations of the network. We demonstrate that our proposed model outperforms the state-of-the-art adaptive networks on CIFAR10, CIFAR100, and ImageNet datasets. The implementation code is available at https://github.com/lee-gwang/EMGNet","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132847219","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}
Graph Convolutional Networks (GCNs) have become the prevailing approach to efficiently learn representations from graph-structured data. Current GCN models adopt a neighborhood aggregation mechanism based on two primary operations, aggregation and combination. The workload of these two processes is determined by the input graph structure, making the graph input the bottleneck of processing GCN. Meanwhile, a large amount of task-irrelevant information in the graphs would hurt the model generalization performance. This brings the opportunity of studying how to remove the redundancy in the graphs. In this paper, we aim to accelerate GCN models by removing the task-irrelevant edges in the graph. We present AdaptiveGCN, an efficient and supervised graph sparsification framework. AdaptiveGCN adopts an edge predictor module to get edge selection strategies by learning the downstream task feedback signals for each GCN layer separately and adaptively in the training stage, then only inference with the selected edges in the test stage to speed up the GCN computation. The experimental results indicate that AdaptiveGCN could yield 43% (on CPU) and 39% (on GPU) GCN model speed-up averagely with comparable model performance on public graph learning benchmarks.
{"title":"AdaptiveGCN","authors":"Dongyue Li, Tao Yang, Lun Du, Zhezhi He, Li Jiang","doi":"10.1145/3459637.3482049","DOIUrl":"https://doi.org/10.1145/3459637.3482049","url":null,"abstract":"Graph Convolutional Networks (GCNs) have become the prevailing approach to efficiently learn representations from graph-structured data. Current GCN models adopt a neighborhood aggregation mechanism based on two primary operations, aggregation and combination. The workload of these two processes is determined by the input graph structure, making the graph input the bottleneck of processing GCN. Meanwhile, a large amount of task-irrelevant information in the graphs would hurt the model generalization performance. This brings the opportunity of studying how to remove the redundancy in the graphs. In this paper, we aim to accelerate GCN models by removing the task-irrelevant edges in the graph. We present AdaptiveGCN, an efficient and supervised graph sparsification framework. AdaptiveGCN adopts an edge predictor module to get edge selection strategies by learning the downstream task feedback signals for each GCN layer separately and adaptively in the training stage, then only inference with the selected edges in the test stage to speed up the GCN computation. The experimental results indicate that AdaptiveGCN could yield 43% (on CPU) and 39% (on GPU) GCN model speed-up averagely with comparable model performance on public graph learning benchmarks.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127586705","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}
Haizhi Yang, Tengyun Wang, Xiaoli Tang, Qianyu Li, Yueyue Shi, Siyu Jiang, Han Yu, Hengjie Song
The rapid rise of real-time bidding-based online advertising has brought significant economic benefits and attracted extensive research attention. From the perspective of an advertiser, it is crucial to perform accurate utility estimation and cost estimation for each individual auction in order to achieve cost-effective advertising. These problems are known as the click through rate (CTR) prediction task and the market price modeling task, respectively. However, existing approaches treat CTR prediction and market price modeling as two independent tasks to be optimized without regard to each other, thus resulting in suboptimal performance. Moreover, they do not make full use of unlabeled data from the losing bids during estimations, which makes them suffer from the sample selection bias issue. To address these limitations, we propose Multi-task Advertising Estimator (MTAE), an end-to-end joint optimization framework which performs both CTR prediction and market price modeling simultaneously. Through multi-task learning, both estimation tasks can take advantage of knowledge transfer to achieve improved feature representation and generalization abilities. In addition, we leverage the abundant bid price signals in the full-volume bid request data and introduce an auxiliary task of predicting the winning probability into the framework for unbiased learning. Through extensive experiments on two large-scale real-world public datasets, we demonstrate that our proposed approach has achieved significant improvements over the state-of-the-art models under various performance metrics.
{"title":"Multi-task Learning for Bias-Free Joint CTR Prediction and Market Price Modeling in Online Advertising","authors":"Haizhi Yang, Tengyun Wang, Xiaoli Tang, Qianyu Li, Yueyue Shi, Siyu Jiang, Han Yu, Hengjie Song","doi":"10.1145/3459637.3482373","DOIUrl":"https://doi.org/10.1145/3459637.3482373","url":null,"abstract":"The rapid rise of real-time bidding-based online advertising has brought significant economic benefits and attracted extensive research attention. From the perspective of an advertiser, it is crucial to perform accurate utility estimation and cost estimation for each individual auction in order to achieve cost-effective advertising. These problems are known as the click through rate (CTR) prediction task and the market price modeling task, respectively. However, existing approaches treat CTR prediction and market price modeling as two independent tasks to be optimized without regard to each other, thus resulting in suboptimal performance. Moreover, they do not make full use of unlabeled data from the losing bids during estimations, which makes them suffer from the sample selection bias issue. To address these limitations, we propose Multi-task Advertising Estimator (MTAE), an end-to-end joint optimization framework which performs both CTR prediction and market price modeling simultaneously. Through multi-task learning, both estimation tasks can take advantage of knowledge transfer to achieve improved feature representation and generalization abilities. In addition, we leverage the abundant bid price signals in the full-volume bid request data and introduce an auxiliary task of predicting the winning probability into the framework for unbiased learning. Through extensive experiments on two large-scale real-world public datasets, we demonstrate that our proposed approach has achieved significant improvements over the state-of-the-art models under various performance metrics.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131177139","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}
Large-scale recommender systems are integral parts of many services. With the recent rapid growth of accessible data, the need for efficient training methods has arisen. Given the high computational cost of training state-of-the-art graph neural network (GNN) based models, it is infeasible to train them from scratch with every new set of interactions. In this work, we present a novel framework for incrementally training GNN-based models. Our framework takes advantage of an experience reply technique built on top of a structurally aware reservoir sampling method tailored for this setting. This framework addresses catastrophic forgetting, allowing the model to preserve its understanding of users' long-term behavioral patterns while adapting to new trends. Our experiments demonstrate the superior performance of our framework on numerous datasets when combined with state-of-the-art GNN-based models.
{"title":"Structure Aware Experience Replay for Incremental Learning in Graph-based Recommender Systems","authors":"Kian Ahrabian, Yishi Xu, Yingxue Zhang, Jiapeng Wu, Yuening Wang, M. Coates","doi":"10.1145/3459637.3482193","DOIUrl":"https://doi.org/10.1145/3459637.3482193","url":null,"abstract":"Large-scale recommender systems are integral parts of many services. With the recent rapid growth of accessible data, the need for efficient training methods has arisen. Given the high computational cost of training state-of-the-art graph neural network (GNN) based models, it is infeasible to train them from scratch with every new set of interactions. In this work, we present a novel framework for incrementally training GNN-based models. Our framework takes advantage of an experience reply technique built on top of a structurally aware reservoir sampling method tailored for this setting. This framework addresses catastrophic forgetting, allowing the model to preserve its understanding of users' long-term behavioral patterns while adapting to new trends. Our experiments demonstrate the superior performance of our framework on numerous datasets when combined with state-of-the-art GNN-based models.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131218673","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}
A. Eldawy, Vagelis Hristidis, Saheli Ghosh, Majid Saeedan, Akil Sevim, A.B. Siddique, Samriddhi Singla, Ganeshram Sivaram, Tin Vu, Yaming Zhang
Book file PDF easily for everyone and every device. You can download and read online Beast file PDF Book only if you are registered here. And also you can download or read online all Book PDF file that related with Beast book. Happy reading Beast Bookeveryone. Download file Free Book PDF Beast at Complete PDF Library. This Book have some digital formats such us :paperbook, ebook, kindle, epub, fb2 and another formats. Here is The Complete PDF Book Library. It's free to register here to get Book file PDF Beast.
{"title":"Beast","authors":"A. Eldawy, Vagelis Hristidis, Saheli Ghosh, Majid Saeedan, Akil Sevim, A.B. Siddique, Samriddhi Singla, Ganeshram Sivaram, Tin Vu, Yaming Zhang","doi":"10.1145/3459637.3481897","DOIUrl":"https://doi.org/10.1145/3459637.3481897","url":null,"abstract":"Book file PDF easily for everyone and every device. You can download and read online Beast file PDF Book only if you are registered here. And also you can download or read online all Book PDF file that related with Beast book. Happy reading Beast Bookeveryone. Download file Free Book PDF Beast at Complete PDF Library. This Book have some digital formats such us :paperbook, ebook, kindle, epub, fb2 and another formats. Here is The Complete PDF Book Library. It's free to register here to get Book file PDF Beast.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133287576","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}
Instance type information is particularly relevant to perform reasoning and obtain further information about entities in knowledge graphs (KGs). However, during automated or pay-as-you-go KG construction processes, instance types might be incomplete or missing in some entities. Previous work focused mostly on representing entities and relations as embeddings based on the statements in the KG. While the computed embeddings encode semantic descriptions and preserve the relationship between the entities, the focus of these methods is often not on predicting schema knowledge, but on predicting missing statements between instances for completing the KG. To fill this gap, we propose an approach that first learns a KG representation suitable for predicting instance type assertions. Then, our solution implements a neural network architecture to predict instance types based on the learned representation. Results show that our representations of entities are much more separable with respect to their associations with classes in the KG, compared to existing methods. For this reason, the performance of predicting instance types on a large number of KGs, in particular on cross-domain KGs with a high variety of classes, is significantly better in terms of F1-score than previous work.
{"title":"Predicting Instance Type Assertions in Knowledge Graphs Using Stochastic Neural Networks","authors":"T. Weller, Maribel Acosta","doi":"10.1145/3459637.3482377","DOIUrl":"https://doi.org/10.1145/3459637.3482377","url":null,"abstract":"Instance type information is particularly relevant to perform reasoning and obtain further information about entities in knowledge graphs (KGs). However, during automated or pay-as-you-go KG construction processes, instance types might be incomplete or missing in some entities. Previous work focused mostly on representing entities and relations as embeddings based on the statements in the KG. While the computed embeddings encode semantic descriptions and preserve the relationship between the entities, the focus of these methods is often not on predicting schema knowledge, but on predicting missing statements between instances for completing the KG. To fill this gap, we propose an approach that first learns a KG representation suitable for predicting instance type assertions. Then, our solution implements a neural network architecture to predict instance types based on the learned representation. Results show that our representations of entities are much more separable with respect to their associations with classes in the KG, compared to existing methods. For this reason, the performance of predicting instance types on a large number of KGs, in particular on cross-domain KGs with a high variety of classes, is significantly better in terms of F1-score than previous work.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133339307","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}
News recommendation is of vital importance to alleviating in-formation overload. Recent research shows that precise modeling of news content and user interests become critical for news rec-ommendation. Existing methods usually utilize information such as news title, abstract, entities to predict Click Through Rate(CTR) or add some auxiliary tasks to a multi-task learning framework. However, none of them directly consider predicted news popularity and the degree of users' attention to popular news into the CTR prediction results. Meanwhile, multiple inter-ests may arise throughout users' browsing history. Thus it is hard to represent user interests via a single user vector. In this paper, we propose PENR, a Popularity-Enhanced News Recommenda-tion method, which integrates popularity prediction task to im-prove the performance of the news encoder. News popularity score is predicted and added to the final CTR, while news popu-larity is utilized to model the degree of users' tendency to follow hot news. Moreover, user interests are modeled from different perspectives via a subspace projection method that assembles the browsing history to multiple subspaces. In this way, we capture users' multi-view interest representations. Experiments on a real-world dataset validate the effectiveness of our PENR approach.
{"title":"Popularity-Enhanced News Recommendation with Multi-View Interest Representation","authors":"Jingkun Wang, Yipu Chen, Zichun Wang, Wen Zhao","doi":"10.1145/3459637.3482462","DOIUrl":"https://doi.org/10.1145/3459637.3482462","url":null,"abstract":"News recommendation is of vital importance to alleviating in-formation overload. Recent research shows that precise modeling of news content and user interests become critical for news rec-ommendation. Existing methods usually utilize information such as news title, abstract, entities to predict Click Through Rate(CTR) or add some auxiliary tasks to a multi-task learning framework. However, none of them directly consider predicted news popularity and the degree of users' attention to popular news into the CTR prediction results. Meanwhile, multiple inter-ests may arise throughout users' browsing history. Thus it is hard to represent user interests via a single user vector. In this paper, we propose PENR, a Popularity-Enhanced News Recommenda-tion method, which integrates popularity prediction task to im-prove the performance of the news encoder. News popularity score is predicted and added to the final CTR, while news popu-larity is utilized to model the degree of users' tendency to follow hot news. Moreover, user interests are modeled from different perspectives via a subspace projection method that assembles the browsing history to multiple subspaces. In this way, we capture users' multi-view interest representations. Experiments on a real-world dataset validate the effectiveness of our PENR approach.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132104493","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}
To inhibit the spread of rumorous information, fact checking aims at retrieving evidence to verify the truthfulness of a given statement. Fact checking methods typically use knowledge graphs (KGs) as external repositories and develop reasoning methods to retrieve evidence from KGs. As real-world statement is often complex and contains multiple claims, multi-claim fact verification is not only necessary but more important for practical applications. However, existing methods only focus on verifying a single claim (i.e. a single-claim statement). Multiple claims imply rich context information and modeling the interrelations between claims can facilitate better verification of a multi-claim statement as a whole. In this paper, we propose a computational method to model inter-claim interactions for multi-claim fact checking. To focus on relevant claims within a statement, our method first extracts topics from the statement and connects the triple claims in the statement to form a claim graph. It then learns a policy-based agent to sequentially select topic-related triples from the claim graph. To fully exploit information from the statement, our method further employs multiple agents and develops a hierarchical attention mechanism to verify multiple claims as a whole. Experimental results on two real-world datasets show the effectiveness of our method for multi-claim fact verification.
{"title":"Modeling Inter-Claim Interactions for Verifying Multiple Claims","authors":"Shuai Wang, W. Mao","doi":"10.1145/3459637.3482144","DOIUrl":"https://doi.org/10.1145/3459637.3482144","url":null,"abstract":"To inhibit the spread of rumorous information, fact checking aims at retrieving evidence to verify the truthfulness of a given statement. Fact checking methods typically use knowledge graphs (KGs) as external repositories and develop reasoning methods to retrieve evidence from KGs. As real-world statement is often complex and contains multiple claims, multi-claim fact verification is not only necessary but more important for practical applications. However, existing methods only focus on verifying a single claim (i.e. a single-claim statement). Multiple claims imply rich context information and modeling the interrelations between claims can facilitate better verification of a multi-claim statement as a whole. In this paper, we propose a computational method to model inter-claim interactions for multi-claim fact checking. To focus on relevant claims within a statement, our method first extracts topics from the statement and connects the triple claims in the statement to form a claim graph. It then learns a policy-based agent to sequentially select topic-related triples from the claim graph. To fully exploit information from the statement, our method further employs multiple agents and develops a hierarchical attention mechanism to verify multiple claims as a whole. Experimental results on two real-world datasets show the effectiveness of our method for multi-claim fact verification.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132571318","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}
Prediction bias is a well-known problem in classification algorithms, which tend to be skewed towards more represented classes. This phenomenon is even more remarkable in multi-label scenarios, where the number of underrepresented classes is usually larger. In light of this, we hereby present the Prediction Bias Coefficient (PBC), a novel measure that aims to assess the bias induced by label imbalance in multi-label classification. The approach leverages Spearman's rank correlation coefficient between the label frequencies and the F-scores obtained for each label individually. After describing the theoretical properties of the proposed indicator, we illustrate its behaviour on a classification task performed with state-of-the-art methods on two real-world datasets, and we compare it experimentally with other metrics described in the literature.
{"title":"Evaluating the Prediction Bias Induced by Label Imbalance in Multi-label Classification","authors":"Luca Piras, Ludovico Boratto, Guilherme Ramos","doi":"10.1145/3459637.3482100","DOIUrl":"https://doi.org/10.1145/3459637.3482100","url":null,"abstract":"Prediction bias is a well-known problem in classification algorithms, which tend to be skewed towards more represented classes. This phenomenon is even more remarkable in multi-label scenarios, where the number of underrepresented classes is usually larger. In light of this, we hereby present the Prediction Bias Coefficient (PBC), a novel measure that aims to assess the bias induced by label imbalance in multi-label classification. The approach leverages Spearman's rank correlation coefficient between the label frequencies and the F-scores obtained for each label individually. After describing the theoretical properties of the proposed indicator, we illustrate its behaviour on a classification task performed with state-of-the-art methods on two real-world datasets, and we compare it experimentally with other metrics described in the literature.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133119073","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：