Graph anomaly detection (GAD) suffers from heterophily — abnormal nodes are sparse so that they are connected to vast normal nodes. The current solutions upon Graph Neural Networks (GNNs) blindly smooth the representation of neiboring nodes, thus undermining the discriminative information of the anomalies. To alleviate the issue, recent studies identify and discard inter-class edges through estimating and comparing the node-level representation similarity. However, the representation of a single node can be misleading when the prediction error is high, thus hindering the performance of the edge indicator. In graph signal processing, the smoothness index is a widely adopted metric which plays the role of frequency in classical spectral analysis. Considering the ground truth Y to be a signal on graph, the smoothness index is equivalent to the value of the heterophily ratio. From this perspective, we aim to address the heterophily problem in the spectral domain. First, we point out that heterophily is positively associated with the frequency of a graph. Towards this end, we could prune inter-class edges by simply emphasizing and delineating the high-frequency components of the graph. Recall that graph Laplacian is a high-pass filter, we adopt it to measure the extent of 1-hop label changing of the center node and indicate high-frequency components. As GAD can be formulated as a semi-supervised binary classification problem, only part of the nodes are labeled. As an alternative, we use the prediction of the nodes to estimate it. Through our analysis, we show that prediction errors are less likely to affect the identification process. Extensive empirical evaluations on four benchmarks demonstrate the effectiveness of the indicator over popular homophilic, heterophilic, and tailored fraud detection methods. Our proposed indicator can effectively reduce the heterophily degree of the graph, thus boosting the overall GAD performance. Codes are open-sourced in https://github.com/blacksingular/GHRN.
{"title":"Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum","authors":"Yuan Gao, Xiang Wang, Xiangnan He, Zhenguang Liu, Huamin Feng, Yongdong Zhang","doi":"10.1145/3543507.3583268","DOIUrl":"https://doi.org/10.1145/3543507.3583268","url":null,"abstract":"Graph anomaly detection (GAD) suffers from heterophily — abnormal nodes are sparse so that they are connected to vast normal nodes. The current solutions upon Graph Neural Networks (GNNs) blindly smooth the representation of neiboring nodes, thus undermining the discriminative information of the anomalies. To alleviate the issue, recent studies identify and discard inter-class edges through estimating and comparing the node-level representation similarity. However, the representation of a single node can be misleading when the prediction error is high, thus hindering the performance of the edge indicator. In graph signal processing, the smoothness index is a widely adopted metric which plays the role of frequency in classical spectral analysis. Considering the ground truth Y to be a signal on graph, the smoothness index is equivalent to the value of the heterophily ratio. From this perspective, we aim to address the heterophily problem in the spectral domain. First, we point out that heterophily is positively associated with the frequency of a graph. Towards this end, we could prune inter-class edges by simply emphasizing and delineating the high-frequency components of the graph. Recall that graph Laplacian is a high-pass filter, we adopt it to measure the extent of 1-hop label changing of the center node and indicate high-frequency components. As GAD can be formulated as a semi-supervised binary classification problem, only part of the nodes are labeled. As an alternative, we use the prediction of the nodes to estimate it. Through our analysis, we show that prediction errors are less likely to affect the identification process. Extensive empirical evaluations on four benchmarks demonstrate the effectiveness of the indicator over popular homophilic, heterophilic, and tailored fraud detection methods. Our proposed indicator can effectively reduce the heterophily degree of the graph, thus boosting the overall GAD performance. Codes are open-sourced in https://github.com/blacksingular/GHRN.","PeriodicalId":296351,"journal":{"name":"Proceedings of the ACM Web Conference 2023","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131447467","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}
Rumaisa Habib, Aimen Inam, Ayesha Ali, I. Qazi, Z. Qazi
Public service websites act as official gateways to services provided by governments. Many of these websites are essential for citizens to receive reliable information and online government services. However, the lack of affordability of mobile broadband services in many developing countries and the rising complexity of websites create barriers for citizens in accessing these government websites. This paper presents the first large-scale analysis of the affordability of public service websites in developing countries. We do this by collecting a corpus of 1900 public service websites, including public websites from nine developing countries and for comparison websites from nine developed countries. Our investigation is driven by website complexity analysis as well as evaluation through a recently proposed affordability index. Our analysis reveals that, in general, public service websites in developing countries do not meet the affordability target set by the UN’s Broadband Commission. However, we show that several countries can be brought within or closer to the affordability target by implementing webpage optimizations to reduce page sizes. We also discuss policy interventions that can help make access to public service website more affordable.
{"title":"A First Look at Public Service Websites from the Affordability Lens","authors":"Rumaisa Habib, Aimen Inam, Ayesha Ali, I. Qazi, Z. Qazi","doi":"10.1145/3543507.3583415","DOIUrl":"https://doi.org/10.1145/3543507.3583415","url":null,"abstract":"Public service websites act as official gateways to services provided by governments. Many of these websites are essential for citizens to receive reliable information and online government services. However, the lack of affordability of mobile broadband services in many developing countries and the rising complexity of websites create barriers for citizens in accessing these government websites. This paper presents the first large-scale analysis of the affordability of public service websites in developing countries. We do this by collecting a corpus of 1900 public service websites, including public websites from nine developing countries and for comparison websites from nine developed countries. Our investigation is driven by website complexity analysis as well as evaluation through a recently proposed affordability index. Our analysis reveals that, in general, public service websites in developing countries do not meet the affordability target set by the UN’s Broadband Commission. However, we show that several countries can be brought within or closer to the affordability target by implementing webpage optimizations to reduce page sizes. We also discuss policy interventions that can help make access to public service website more affordable.","PeriodicalId":296351,"journal":{"name":"Proceedings of the ACM Web Conference 2023","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133794414","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}
Zainab Akhtar, Umair Qazi, Rizwan Sadiq, Aya El-Sakka, M. Sajjad, Ferda Ofli, Muhammad Imran
The devastating 2022 floods in Pakistan resulted in a catastrophe impacting millions of people and destroying thousands of homes. While disaster management efforts were taken, crisis responders struggled to understand the country-wide flood extent, population exposure, urgent needs of affected people, and various types of damage. To tackle this challenge, we leverage remote and social sensing with geospatial data using state-of-the-art machine learning techniques for text and image processing. Our satellite-based analysis over a one-month period (25 Aug–25 Sep) revealed that 11.48% of Pakistan was inundated. When combined with geospatial data, this meant 18.9 million people were at risk across 160 districts in Pakistan, with adults constituting 50% of the exposed population. Our social sensing data analysis surfaced 106.7k reports pertaining to deaths, injuries, and concerns of the affected people. To understand the urgent needs of the affected population, we analyzed tweet texts and found that South Karachi, Chitral and North Waziristan required the most basic necessities like food and shelter. Further analysis of tweet images revealed that Lasbela, Rajanpur, and Jhal Magsi had the highest damage reports normalized by their population. These damage reports were found to correlate strongly with affected people reports and need reports, achieving an R-Square of 0.96 and 0.94, respectively. Our extensive study shows that combining remote sensing, social sensing, and geospatial data can provide accurate and timely information during a disaster event, which is crucial in prioritizing areas for immediate and gradual response.
{"title":"Mapping Flood Exposure, Damage, and Population Needs Using Remote and Social Sensing: A Case Study of 2022 Pakistan Floods","authors":"Zainab Akhtar, Umair Qazi, Rizwan Sadiq, Aya El-Sakka, M. Sajjad, Ferda Ofli, Muhammad Imran","doi":"10.1145/3543507.3583881","DOIUrl":"https://doi.org/10.1145/3543507.3583881","url":null,"abstract":"The devastating 2022 floods in Pakistan resulted in a catastrophe impacting millions of people and destroying thousands of homes. While disaster management efforts were taken, crisis responders struggled to understand the country-wide flood extent, population exposure, urgent needs of affected people, and various types of damage. To tackle this challenge, we leverage remote and social sensing with geospatial data using state-of-the-art machine learning techniques for text and image processing. Our satellite-based analysis over a one-month period (25 Aug–25 Sep) revealed that 11.48% of Pakistan was inundated. When combined with geospatial data, this meant 18.9 million people were at risk across 160 districts in Pakistan, with adults constituting 50% of the exposed population. Our social sensing data analysis surfaced 106.7k reports pertaining to deaths, injuries, and concerns of the affected people. To understand the urgent needs of the affected population, we analyzed tweet texts and found that South Karachi, Chitral and North Waziristan required the most basic necessities like food and shelter. Further analysis of tweet images revealed that Lasbela, Rajanpur, and Jhal Magsi had the highest damage reports normalized by their population. These damage reports were found to correlate strongly with affected people reports and need reports, achieving an R-Square of 0.96 and 0.94, respectively. Our extensive study shows that combining remote sensing, social sensing, and geospatial data can provide accurate and timely information during a disaster event, which is crucial in prioritizing areas for immediate and gradual response.","PeriodicalId":296351,"journal":{"name":"Proceedings of the ACM Web Conference 2023","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114805101","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}
Zhenyan Li, Yancheng Dong, Chen Gao, Yizhou Zhao, Dong Li, Jianye Hao, Kai Zhang, Yong Li, Zhi Wang
In the information-overloaded era of the Web, recommender systems that provide personalized content filtering are now the mainstream portal for users to access Web information. Recommender systems deploy machine learning models to learn users’ preferences from collected historical data, leading to more centralized recommendation results due to the feedback loop. As a result, it will harm the ranking of content outside the narrowed scope and limit the options seen by users. In this work, we first conduct data analysis from a graph view to observe that the users’ feedback is restricted to limited items, verifying the phenomenon of centralized recommendation. We further develop a general simulation framework to derive the procedure of the recommender system, including data collection, model learning, and item exposure, which forms a loop. To address the filter bubble issue under the feedback loop, we then propose a general and easy-to-use reinforcement learning-based method, which can adaptively select few but effective connections between nodes from different communities as the exposure list. We conduct extensive experiments in the simulation framework based on large-scale real-world datasets. The results demonstrate that our proposed reinforcement learning-based control method can serve as an effective solution to alleviate the filter bubble and the separated communities induced by it. We believe the proposed framework of controllable recommendation in this work can inspire not only the researchers of recommender systems, but also a broader community concerned with artificial intelligence algorithms’ impact on humanity, especially for those vulnerable populations on the Web.
{"title":"Breaking Filter Bubble: A Reinforcement Learning Framework of Controllable Recommender System","authors":"Zhenyan Li, Yancheng Dong, Chen Gao, Yizhou Zhao, Dong Li, Jianye Hao, Kai Zhang, Yong Li, Zhi Wang","doi":"10.1145/3543507.3583856","DOIUrl":"https://doi.org/10.1145/3543507.3583856","url":null,"abstract":"In the information-overloaded era of the Web, recommender systems that provide personalized content filtering are now the mainstream portal for users to access Web information. Recommender systems deploy machine learning models to learn users’ preferences from collected historical data, leading to more centralized recommendation results due to the feedback loop. As a result, it will harm the ranking of content outside the narrowed scope and limit the options seen by users. In this work, we first conduct data analysis from a graph view to observe that the users’ feedback is restricted to limited items, verifying the phenomenon of centralized recommendation. We further develop a general simulation framework to derive the procedure of the recommender system, including data collection, model learning, and item exposure, which forms a loop. To address the filter bubble issue under the feedback loop, we then propose a general and easy-to-use reinforcement learning-based method, which can adaptively select few but effective connections between nodes from different communities as the exposure list. We conduct extensive experiments in the simulation framework based on large-scale real-world datasets. The results demonstrate that our proposed reinforcement learning-based control method can serve as an effective solution to alleviate the filter bubble and the separated communities induced by it. We believe the proposed framework of controllable recommendation in this work can inspire not only the researchers of recommender systems, but also a broader community concerned with artificial intelligence algorithms’ impact on humanity, especially for those vulnerable populations on the Web.","PeriodicalId":296351,"journal":{"name":"Proceedings of the ACM Web Conference 2023","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116946580","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 online games, predicting massive battle outcomes is a fundamental task of many applications, such as team optimization and tactical formulation. Existing works do not pay adequate attention to the massive battle. They either seek to evaluate individuals in isolation or mine simple pair-wise interactions between individuals, neither of which effectively captures the intricate interactions between massive units (e.g., individuals). Furthermore, as the team size increases, the phenomenon of diminishing marginal utility of units emerges. Such a diminishing pattern is rarely noticed in previous work, and how to capture it from data remains a challenge. To this end, we propose a novel Massive battle outcome predictor with margiNal Effect modules, namely MassNE, which comprehensively incorporates individual effects, cooperation effects (i.e., intra-team interactions) and suppression effects (i.e., inter-team interactions) for predicting battle outcomes. Specifically, we design marginal effect modules to learn how units’ marginal utility changing respect to their number, where the monotonicity assumption is applied to ensure rationality. In addition, we evaluate the current classical models and provide mathematical proofs that MassNE is able to generalize several earlier works in massive settings. Massive battle datasets generated by StarCraft II APIs are adopted to evaluate the performances of MassNE. Extensive experiments empirically demonstrate the effectiveness of MassNE, and MassNE can reveal reasonable cooperation effects, suppression effects, and marginal utilities of combat units from the data.
{"title":"MassNE: Exploring Higher-Order Interactions with Marginal Effect for Massive Battle Outcome Prediction","authors":"Yin Gu, Kai Zhang, Qi Liu, Xin Lin, Zhenya Huang, Enhong Chen","doi":"10.1145/3543507.3583390","DOIUrl":"https://doi.org/10.1145/3543507.3583390","url":null,"abstract":"In online games, predicting massive battle outcomes is a fundamental task of many applications, such as team optimization and tactical formulation. Existing works do not pay adequate attention to the massive battle. They either seek to evaluate individuals in isolation or mine simple pair-wise interactions between individuals, neither of which effectively captures the intricate interactions between massive units (e.g., individuals). Furthermore, as the team size increases, the phenomenon of diminishing marginal utility of units emerges. Such a diminishing pattern is rarely noticed in previous work, and how to capture it from data remains a challenge. To this end, we propose a novel Massive battle outcome predictor with margiNal Effect modules, namely MassNE, which comprehensively incorporates individual effects, cooperation effects (i.e., intra-team interactions) and suppression effects (i.e., inter-team interactions) for predicting battle outcomes. Specifically, we design marginal effect modules to learn how units’ marginal utility changing respect to their number, where the monotonicity assumption is applied to ensure rationality. In addition, we evaluate the current classical models and provide mathematical proofs that MassNE is able to generalize several earlier works in massive settings. Massive battle datasets generated by StarCraft II APIs are adopted to evaluate the performances of MassNE. Extensive experiments empirically demonstrate the effectiveness of MassNE, and MassNE can reveal reasonable cooperation effects, suppression effects, and marginal utilities of combat units from the data.","PeriodicalId":296351,"journal":{"name":"Proceedings of the ACM Web Conference 2023","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117228726","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 generative models are recently gaining significant interest in current application domains. They are commonly used to model social networks, knowledge graphs, and protein-protein interaction networks. In this talk we will present the potential of graph generative models and our recent relevant efforts in the biomedical domain. More specifically we present a novel architecture that generates medical records as graphs with privacy guarantees. We capitalize and modify the graph Variational autoencoders (VAEs) architecture. We train the generative model with the well known MIMIC medical database and achieve generated data that are very similar to the real ones yet provide privacy guarantees. We also develop new GNNs for predicting antibiotic resistance and other protein related downstream tasks such as enzymes classifications and Gene Ontology classification. We achieve there as well promising results with potential for future application in broader biomedical related tasks. Finally we present future research directions for multi modal generative models involving graphs.
{"title":"GNNs and Graph Generative models for biomedical applications","authors":"M. Vazirgiannis","doi":"10.1145/3543507.3593049","DOIUrl":"https://doi.org/10.1145/3543507.3593049","url":null,"abstract":"Graph generative models are recently gaining significant interest in current application domains. They are commonly used to model social networks, knowledge graphs, and protein-protein interaction networks. In this talk we will present the potential of graph generative models and our recent relevant efforts in the biomedical domain. More specifically we present a novel architecture that generates medical records as graphs with privacy guarantees. We capitalize and modify the graph Variational autoencoders (VAEs) architecture. We train the generative model with the well known MIMIC medical database and achieve generated data that are very similar to the real ones yet provide privacy guarantees. We also develop new GNNs for predicting antibiotic resistance and other protein related downstream tasks such as enzymes classifications and Gene Ontology classification. We achieve there as well promising results with potential for future application in broader biomedical related tasks. Finally we present future research directions for multi modal generative models involving graphs.","PeriodicalId":296351,"journal":{"name":"Proceedings of the ACM Web Conference 2023","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123707653","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}
Guoshan Lu, Haobo Wang, Saisai Yang, Jing Yuan, Guozheng Yang, Cheng Zang, Gang Chen, J. Zhao
Feature engineering often plays a crucial role in building mining systems for tabular data, which traditionally requires experienced human experts to perform. Thanks to the rapid advances in reinforcement learning, it has offered an automated alternative, i.e. automated feature engineering (AutoFE). In this work, through scrutiny of the prior AutoFE methods, we characterize several research challenges that remained in this regime, concerning system-wide efficiency, efficacy, and practicality toward production. We then propose Catch, a full-fledged new AutoFE framework that comprehensively addresses the aforementioned challenges. The core to Catch composes a hierarchical-policy reinforcement learning scheme that manifests a collaborative feature engineering exploration and exploitation grounded on the granularity of the whole feature set. At a higher level of the hierarchy, a decision-making module controls the post-processing of the attained feature engineering transformation. We extensively experiment with Catch on 26 academic standardized tabular datasets and 9 industrialized real-world datasets. Measured by numerous metrics and analyses, Catch establishes a new state-of-the-art, from perspectives performance, latency as well as its practicality towards production. Source code1 can be found at https://github.com/1171000709/Catch.
{"title":"Catch: Collaborative Feature Set Search for Automated Feature Engineering","authors":"Guoshan Lu, Haobo Wang, Saisai Yang, Jing Yuan, Guozheng Yang, Cheng Zang, Gang Chen, J. Zhao","doi":"10.1145/3543507.3583527","DOIUrl":"https://doi.org/10.1145/3543507.3583527","url":null,"abstract":"Feature engineering often plays a crucial role in building mining systems for tabular data, which traditionally requires experienced human experts to perform. Thanks to the rapid advances in reinforcement learning, it has offered an automated alternative, i.e. automated feature engineering (AutoFE). In this work, through scrutiny of the prior AutoFE methods, we characterize several research challenges that remained in this regime, concerning system-wide efficiency, efficacy, and practicality toward production. We then propose Catch, a full-fledged new AutoFE framework that comprehensively addresses the aforementioned challenges. The core to Catch composes a hierarchical-policy reinforcement learning scheme that manifests a collaborative feature engineering exploration and exploitation grounded on the granularity of the whole feature set. At a higher level of the hierarchy, a decision-making module controls the post-processing of the attained feature engineering transformation. We extensively experiment with Catch on 26 academic standardized tabular datasets and 9 industrialized real-world datasets. Measured by numerous metrics and analyses, Catch establishes a new state-of-the-art, from perspectives performance, latency as well as its practicality towards production. Source code1 can be found at https://github.com/1171000709/Catch.","PeriodicalId":296351,"journal":{"name":"Proceedings of the ACM Web Conference 2023","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117206012","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}
S. Wijenayake, Danula Hettiachchi, Jorge Gonçalves
Optimising the assignment of tasks to workers is an effective approach to ensure high quality in crowdsourced data - particularly in heterogeneous micro tasks. However, previous attempts at heterogeneous micro task assignment based on worker characteristics are limited to using cognitive skills, despite literature emphasising that worker performance varies based on other parameters. This study is an initial step towards understanding whether and how multiple parameters such as cognitive skills, mood, personality, alertness, comprehension skill, and social and physical context of workers can be leveraged in tandem to improve worker performance estimations in heterogeneous micro tasks. Our predictive models indicate that these parameters have varying effects on worker performance in the five task types considered – sentiment analysis, classification, transcription, named entity recognition and bounding box. Moreover, we note 0.003 - 0.018 reduction in mean absolute error of predicted worker accuracy across all tasks, when task assignment is based on models that consider all parameters vs. models that only consider workers’ cognitive skills. Our findings pave the way for the use of holistic approaches in micro task assignment that effectively quantify worker context.
{"title":"Combining Worker Factors for Heterogeneous Crowd Task Assignment","authors":"S. Wijenayake, Danula Hettiachchi, Jorge Gonçalves","doi":"10.1145/3543507.3583190","DOIUrl":"https://doi.org/10.1145/3543507.3583190","url":null,"abstract":"Optimising the assignment of tasks to workers is an effective approach to ensure high quality in crowdsourced data - particularly in heterogeneous micro tasks. However, previous attempts at heterogeneous micro task assignment based on worker characteristics are limited to using cognitive skills, despite literature emphasising that worker performance varies based on other parameters. This study is an initial step towards understanding whether and how multiple parameters such as cognitive skills, mood, personality, alertness, comprehension skill, and social and physical context of workers can be leveraged in tandem to improve worker performance estimations in heterogeneous micro tasks. Our predictive models indicate that these parameters have varying effects on worker performance in the five task types considered – sentiment analysis, classification, transcription, named entity recognition and bounding box. Moreover, we note 0.003 - 0.018 reduction in mean absolute error of predicted worker accuracy across all tasks, when task assignment is based on models that consider all parameters vs. models that only consider workers’ cognitive skills. Our findings pave the way for the use of holistic approaches in micro task assignment that effectively quantify worker context.","PeriodicalId":296351,"journal":{"name":"Proceedings of the ACM Web Conference 2023","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128273319","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}
With the explosive growth of video and text data on the web, text-video retrieval has become a vital task for online video platforms. Recently, text-video retrieval methods based on pre-trained models have attracted a lot of attention. However, existing methods cannot effectively capture the fine-grained information in videos, and typically suffer from the hubness problem where a collection of similar videos are retrieved by a large number of different queries. In this paper, we propose Match4Match, a new text-video retrieval method based on CLIP (Contrastive Language-Image Pretraining) and graph optimization theories. To balance calculation efficiency and model accuracy, Match4Match seamlessly supports three inference modes for different application scenarios. In fast vector retrieval mode, we embed texts and videos in the same space and employ a vector retrieval engine to obtain the top K videos. In fine-grained alignment mode, our method fully utilizes the pre-trained knowledge of the CLIP model to align words with corresponding video frames, and uses the fine-grained information to compute text-video similarity more accurately. In flow-style matching mode, to alleviate the detrimental impact of the hubness problem, we model the retrieval problem as a combinatorial optimization problem and solve it using maximum flow with minimum cost algorithm. To demonstrate the effectiveness of our method, we conduct experiments on five public text-video datasets. The overall performance of our proposed method outperforms state-of-the-art methods. Additionally, we evaluate the computational efficiency of Match4Match. Benefiting from the three flexible inference modes, Match4Match can respond to a large number of query requests with low latency or achieve high recall with acceptable time consumption.
{"title":"Match4Match: Enhancing Text-Video Retrieval by Maximum Flow with Minimum Cost","authors":"Zhongjie Duan, Chengyu Wang, Cen Chen, Wenmeng Zhou, Jun Huang, Weining Qian","doi":"10.1145/3543507.3583365","DOIUrl":"https://doi.org/10.1145/3543507.3583365","url":null,"abstract":"With the explosive growth of video and text data on the web, text-video retrieval has become a vital task for online video platforms. Recently, text-video retrieval methods based on pre-trained models have attracted a lot of attention. However, existing methods cannot effectively capture the fine-grained information in videos, and typically suffer from the hubness problem where a collection of similar videos are retrieved by a large number of different queries. In this paper, we propose Match4Match, a new text-video retrieval method based on CLIP (Contrastive Language-Image Pretraining) and graph optimization theories. To balance calculation efficiency and model accuracy, Match4Match seamlessly supports three inference modes for different application scenarios. In fast vector retrieval mode, we embed texts and videos in the same space and employ a vector retrieval engine to obtain the top K videos. In fine-grained alignment mode, our method fully utilizes the pre-trained knowledge of the CLIP model to align words with corresponding video frames, and uses the fine-grained information to compute text-video similarity more accurately. In flow-style matching mode, to alleviate the detrimental impact of the hubness problem, we model the retrieval problem as a combinatorial optimization problem and solve it using maximum flow with minimum cost algorithm. To demonstrate the effectiveness of our method, we conduct experiments on five public text-video datasets. The overall performance of our proposed method outperforms state-of-the-art methods. Additionally, we evaluate the computational efficiency of Match4Match. Benefiting from the three flexible inference modes, Match4Match can respond to a large number of query requests with low latency or achieve high recall with acceptable time consumption.","PeriodicalId":296351,"journal":{"name":"Proceedings of the ACM Web Conference 2023","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129916676","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}
Dynamic link prediction is essential for a wide range of domains, including social networks, bioinformatics, knowledge bases, and recommender systems. Existing works have demonstrated that structural information and temporal information are two of the most important information for this problem. However, existing works either focus on modeling them independently or modeling the temporal dynamics of a single structural scale, neglecting the complex correlations among them. This paper proposes to model the inherent correlations among the evolving dynamics of different structural scales for dynamic link prediction. Following this idea, we propose an Attentional Multi-scale Co-evolving Network (AMCNet). Specifically, We model multi-scale structural information by a motif-based graph neural network with multi-scale pooling. Then, we design a hierarchical attention-based sequence-to-sequence model for learning the complex correlations among the evolution dynamics of different structural scales. Extensive experiments on four real-world datasets with different characteristics demonstrate that AMCNet significantly outperforms the state-of-the-art in both single-step and multi-step dynamic link prediction tasks.
{"title":"An Attentional Multi-scale Co-evolving Model for Dynamic Link Prediction","authors":"Guozhen Zhang, Tian Ye, Depeng Jin, Yong Li","doi":"10.1145/3543507.3583396","DOIUrl":"https://doi.org/10.1145/3543507.3583396","url":null,"abstract":"Dynamic link prediction is essential for a wide range of domains, including social networks, bioinformatics, knowledge bases, and recommender systems. Existing works have demonstrated that structural information and temporal information are two of the most important information for this problem. However, existing works either focus on modeling them independently or modeling the temporal dynamics of a single structural scale, neglecting the complex correlations among them. This paper proposes to model the inherent correlations among the evolving dynamics of different structural scales for dynamic link prediction. Following this idea, we propose an Attentional Multi-scale Co-evolving Network (AMCNet). Specifically, We model multi-scale structural information by a motif-based graph neural network with multi-scale pooling. Then, we design a hierarchical attention-based sequence-to-sequence model for learning the complex correlations among the evolution dynamics of different structural scales. Extensive experiments on four real-world datasets with different characteristics demonstrate that AMCNet significantly outperforms the state-of-the-art in both single-step and multi-step dynamic link prediction tasks.","PeriodicalId":296351,"journal":{"name":"Proceedings of the ACM Web Conference 2023","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130070890","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：