Pub Date : 2024-12-27DOI: 10.1109/TKDE.2024.3518359
Ya-Wen Teng;Yishuo Shi;De-Nian Yang;Chih-Hua Tai;Philip S. Yu;Ming-Syan Chen
In this paper, we address the problem of revenue maximization (RM) for multi-grade products in social networks by considering pricing, seed selection, and coupon distribution. Previous works on RM often focus on a single product and neglect the use of coupons for promotion. We propose a new optimization problem, Revenue Maximization of Multi-Grade Product(RMMGP), to simultaneously determine pricing, seed selection, and coupon distribution for multi-grade products with both promotional and competitive relationships between grades in order to maximize revenue through viral marketing. We prove the hardness and inapproximability of RMMGP and show that the revenue function is not monotone or submodular. To solve RMMGP, we design an approximation algorithm, namely Data-Dependent Revenue Maximization (DDRM), and propose the Pricing-Seeding-Coupon allocation (PriSCa) algorithm, which uses the concepts of Worth Receiving Probability, Pricing-Promotion Alternating Framework, and Independent/Holistic Customer-Grade Determinant sets. Our experiments on real social networks, using valuation distributions from Amazon.com, demonstrate that PriSCa and DDRM achieve on average 1.5 times higher revenue than state-of-the-art approaches. Additionally, PriSCa is efficient and scalable on large datasets.
{"title":"Multi-Grade Revenue Maximization for Promotional and Competitive Viral Marketing in Social Networks","authors":"Ya-Wen Teng;Yishuo Shi;De-Nian Yang;Chih-Hua Tai;Philip S. Yu;Ming-Syan Chen","doi":"10.1109/TKDE.2024.3518359","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3518359","url":null,"abstract":"In this paper, we address the problem of revenue maximization (RM) for multi-grade products in social networks by considering pricing, seed selection, and coupon distribution. Previous works on RM often focus on a single product and neglect the use of coupons for promotion. We propose a new optimization problem, <italic>Revenue Maximization of Multi-Grade Product(RMMGP)</i>, to simultaneously determine pricing, seed selection, and coupon distribution for multi-grade products with both promotional and competitive relationships between grades in order to maximize revenue through viral marketing. We prove the hardness and inapproximability of RMMGP and show that the revenue function is not monotone or submodular. To solve RMMGP, we design an approximation algorithm, namely <italic>Data-Dependent Revenue Maximization (DDRM)</i>, and propose the <italic>Pricing-Seeding-Coupon allocation (PriSCa)</i> algorithm, which uses the concepts of Worth Receiving Probability, Pricing-Promotion Alternating Framework, and Independent/Holistic Customer-Grade Determinant sets. Our experiments on real social networks, using valuation distributions from Amazon.com, demonstrate that PriSCa and DDRM achieve on average 1.5 times higher revenue than state-of-the-art approaches. Additionally, PriSCa is efficient and scalable on large datasets.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1339-1353"},"PeriodicalIF":8.9,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-27DOI: 10.1109/TKDE.2024.3523472
Shenghong He;Chao Yu;Qian Lin;Shangqin Mao;Bo Tang;Qianlong Xie;Xingxing Wang
Real-time bidding (RTB) plays a pivotal role in online advertising ecosystems. Advertisers employ strategic bidding to optimize their advertising impact while adhering to various financial constraints, such as the return-on-investment (ROI) and cost-per-click (CPC). Primarily focusing on bidding with fixed budget constraints, traditional approaches cannot effectively manage the dynamic budget allocation problem where the goal is to achieve global optimization of bidding performance across multiple channels with a shared budget. In this paper, we propose a hierarchical multi-agent reinforcement learning framework for multi-channel bidding optimization. In this framework, the top-level strategy applies a CPC constrained diffusion model to dynamically allocate budgets among the channels according to their distinct features and complex interdependencies, while the bottom-level strategy adopts a state-action decoupled actor-critic method to address the problem of extrapolation errors in offline learning caused by out-of-distribution actions and a context-based meta-channel knowledge learning method to improve the state representation capability of the policy based on the shared knowledge among different channels. Comprehensive experiments conducted on a large scale real-world industrial dataset from the Meituan ad bidding platform demonstrate that our method achieves a state-of-the-art performance.
{"title":"Hierarchical Multi-Agent Meta-Reinforcement Learning for Cross-Channel Bidding","authors":"Shenghong He;Chao Yu;Qian Lin;Shangqin Mao;Bo Tang;Qianlong Xie;Xingxing Wang","doi":"10.1109/TKDE.2024.3523472","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3523472","url":null,"abstract":"Real-time bidding (RTB) plays a pivotal role in online advertising ecosystems. Advertisers employ strategic bidding to optimize their advertising impact while adhering to various financial constraints, such as the return-on-investment (ROI) and cost-per-click (CPC). Primarily focusing on bidding with fixed budget constraints, traditional approaches cannot effectively manage the dynamic budget allocation problem where the goal is to achieve global optimization of bidding performance across multiple channels with a shared budget. In this paper, we propose a hierarchical multi-agent reinforcement learning framework for multi-channel bidding optimization. In this framework, the top-level strategy applies a CPC constrained diffusion model to dynamically allocate budgets among the channels according to their distinct features and complex interdependencies, while the bottom-level strategy adopts a state-action decoupled actor-critic method to address the problem of extrapolation errors in offline learning caused by out-of-distribution actions and a context-based meta-channel knowledge learning method to improve the state representation capability of the policy based on the shared knowledge among different channels. Comprehensive experiments conducted on a large scale real-world industrial dataset from the Meituan ad bidding platform demonstrate that our method achieves a state-of-the-art performance.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1241-1254"},"PeriodicalIF":8.9,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-27DOI: 10.1109/TKDE.2024.3523399
Xueqi Cheng;Yuanzheng Wang;Yixing Fan;Jiafeng Guo;Ruqing Zhang;Keping Bi
Entity linking (EL) is a challenging task as it typically requires matching an ambiguous entity mention with its corresponding entity in a knowledge base (KB). The mainstream studies focus on learning and evaluating linking models on the same corpus and obtained significant performance achievement, however, they often overlook the generalization ability to out-of-domain corpus, which is more realistic yet much more challenging. To address this issue, we introduce a novel neural-symbolic model for entity linking, which is inspired by the symbol-manipulation mechanism in human brains. Specifically, we abstract diverse features into unified variables, then combine them using neural operators to capture diverse relevance requirements, and finally aggregate relevance scores through voting. We conduct experiments on eleven benchmark datasets with different types of text, and the results show that our method outperforms nearly all baselines. Notably, the best performance of our method on seven out-of-domain datasets highlights its generalization ability.
{"title":"GSM-EL: A Generalizable Symbol-Manipulation Approach for Entity Linking","authors":"Xueqi Cheng;Yuanzheng Wang;Yixing Fan;Jiafeng Guo;Ruqing Zhang;Keping Bi","doi":"10.1109/TKDE.2024.3523399","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3523399","url":null,"abstract":"Entity linking (EL) is a challenging task as it typically requires matching an ambiguous entity mention with its corresponding entity in a knowledge base (KB). The mainstream studies focus on learning and evaluating linking models on the same corpus and obtained significant performance achievement, however, they often overlook the generalization ability to out-of-domain corpus, which is more realistic yet much more challenging. To address this issue, we introduce a novel neural-symbolic model for entity linking, which is inspired by the symbol-manipulation mechanism in human brains. Specifically, we abstract diverse features into unified variables, then combine them using neural operators to capture diverse relevance requirements, and finally aggregate relevance scores through voting. We conduct experiments on eleven benchmark datasets with different types of text, and the results show that our method outperforms nearly all baselines. Notably, the best performance of our method on seven out-of-domain datasets highlights its generalization ability.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1213-1226"},"PeriodicalIF":8.9,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-26DOI: 10.1109/TKDE.2024.3523034
Wenfei Wu;Yuchen Xu
In distributed data stream mining, we abstract a MIMO scenario where a stream of multiple items is mined by multiple nodes. We design a framework named MimoSketch for the MIMO-specific scenario, which improves the fundamental mining tasks of item frequency estimation, item size distribution estimation, heavy hitter detection, heavy change detection, and entropy estimation. MimoSketch consists of an algorithm design and a policy to schedule items to nodes. MimoSketch's algorithm applies random counting to preserve a mathematically proven unbiasedness property, which makes it friendly to the aggregate query on multiple nodes; its memory layout is dynamically adaptive to the runtime item size distribution, which maximizes the estimation accuracy by storing more items. MimoSketch's scheduling policy balances items among nodes, avoiding nodes being overloaded or underloaded, which improves the overall mining accuracy. Our prototype and evaluation show that our algorithm can improve the accuracy of five typical mining tasks by an order of magnitude compared with the state-of-the-art solutions, and the scheduling policy further promotes the performance in MIMO scenarios.
{"title":"MimoSketch: A Framework for Frequency-Based Mining Tasks on Multiple Nodes With Sketches","authors":"Wenfei Wu;Yuchen Xu","doi":"10.1109/TKDE.2024.3523034","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3523034","url":null,"abstract":"In distributed data stream mining, we abstract a MIMO scenario where a stream of <underline>m</u>ultiple <underline>i</u>tems is mined by <underline>m</u>ultiple n<underline>o</u>des. We design a framework named MimoSketch for the MIMO-specific scenario, which improves the fundamental mining tasks of item frequency estimation, item size distribution estimation, heavy hitter detection, heavy change detection, and entropy estimation. MimoSketch consists of an algorithm design and a policy to schedule items to nodes. MimoSketch's algorithm applies random counting to preserve a mathematically proven <italic>unbiasedness</i> property, which makes it friendly to the aggregate query on multiple nodes; its memory layout is <italic>dynamically</i> adaptive to the runtime item size distribution, which maximizes the estimation accuracy by storing more items. MimoSketch's scheduling policy balances items among nodes, avoiding nodes being overloaded or underloaded, which improves the overall mining accuracy. Our prototype and evaluation show that our algorithm can improve the accuracy of five typical mining tasks by an order of magnitude compared with the state-of-the-art solutions, and the scheduling policy further promotes the performance in MIMO scenarios.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1311-1324"},"PeriodicalIF":8.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-26DOI: 10.1109/TKDE.2024.3522975
Weichao Yan;Hao Ma;Zaiyue Yang
In recent years, sequence prediction, particularly in natural language processing tasks, has made significant progress due to advanced neural network architectures like Transformer and enhanced computing power. However, challenges persist in modeling and analyzing certain types of sequence data, such as human daily activities and competitive ball games. These segmented sequence data are characterized by short length, varying local dependencies, and coarse-grained unit states. These characteristics limit the effectiveness of conventional probabilistic graphical models and attention-based or recurrent neural networks in modeling and analyzing segmented sequence data. To address this gap, we introduce a novel generative model for segmented sequences, employing an ensemble of multiple variable-order Markov models (VOMMs) to flexibly represent state transition dependencies. Our approach integrates probabilistic graphical models with neural networks, surpassing the representation capabilities of single high-order or variable-order Markov models. Compared to end-to-end deep learning models, our method offers improved interpretability and reduces overfitting in short segments. We demonstrate the efficacy of our proposed method in two tasks: predicting tennis shot types and forecasting daily action sequences. These applications highlight the broad applicability of our segmented sequence modeling approach across diverse domains.
{"title":"Segmented Sequence Prediction Using Variable-Order Markov Model Ensemble","authors":"Weichao Yan;Hao Ma;Zaiyue Yang","doi":"10.1109/TKDE.2024.3522975","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3522975","url":null,"abstract":"In recent years, sequence prediction, particularly in natural language processing tasks, has made significant progress due to advanced neural network architectures like Transformer and enhanced computing power. However, challenges persist in modeling and analyzing certain types of sequence data, such as human daily activities and competitive ball games. These segmented sequence data are characterized by short length, varying local dependencies, and coarse-grained unit states. These characteristics limit the effectiveness of conventional probabilistic graphical models and attention-based or recurrent neural networks in modeling and analyzing segmented sequence data. To address this gap, we introduce a novel generative model for segmented sequences, employing an ensemble of multiple variable-order Markov models (VOMMs) to flexibly represent state transition dependencies. Our approach integrates probabilistic graphical models with neural networks, surpassing the representation capabilities of single high-order or variable-order Markov models. Compared to end-to-end deep learning models, our method offers improved interpretability and reduces overfitting in short segments. We demonstrate the efficacy of our proposed method in two tasks: predicting tennis shot types and forecasting daily action sequences. These applications highlight the broad applicability of our segmented sequence modeling approach across diverse domains.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1425-1438"},"PeriodicalIF":8.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-26DOI: 10.1109/TKDE.2024.3523383
Liangmin Guo;Shiming Zhou;Haiyue Tang;Xiaoyao Zheng;Yonglong Luo
Most current session-based recommendations model session sequences solely based on the user's target behavior, ignoring the user's hidden preferences in auxiliary behaviors. Additionally, they use ordinary graphs to model one-to-one item correlations in the current session and fail to leverage other sessions to learn richer higher-order item correlations. To address these issues, a multi-behavior hypergraph contrastive learning model for session-based recommendations is proposed. This model represents all the sessions as global hypergraphs according to two types of behavior sequences. It employs contrastive learning to obtain global item embeddings, which are further aggregated to generate a global session representation that captures higher-order correlations of items from all session perspectives. A novel local heterogeneous hypergraph is designed for the current session to capture higher-order correlations between items with different behaviors in the current session, thus enhancing the local session representation. Additionally, a novel self-supervised signal is created by constructing a multi-behavior line graph, enhancing the global session representation. Finally, the local session representation, global session representation, and global item embedding are used to learn the predicted interaction probability of each item. Extensive experiments are conducted on three real datasets, and the results demonstrate that the proposed model significantly improves recommendation accuracy.
{"title":"Multi-Behavior Hypergraph Contrastive Learning for Session-Based Recommendation","authors":"Liangmin Guo;Shiming Zhou;Haiyue Tang;Xiaoyao Zheng;Yonglong Luo","doi":"10.1109/TKDE.2024.3523383","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3523383","url":null,"abstract":"Most current session-based recommendations model session sequences solely based on the user's target behavior, ignoring the user's hidden preferences in auxiliary behaviors. Additionally, they use ordinary graphs to model one-to-one item correlations in the current session and fail to leverage other sessions to learn richer higher-order item correlations. To address these issues, a multi-behavior hypergraph contrastive learning model for session-based recommendations is proposed. This model represents all the sessions as global hypergraphs according to two types of behavior sequences. It employs contrastive learning to obtain global item embeddings, which are further aggregated to generate a global session representation that captures higher-order correlations of items from all session perspectives. A novel local heterogeneous hypergraph is designed for the current session to capture higher-order correlations between items with different behaviors in the current session, thus enhancing the local session representation. Additionally, a novel self-supervised signal is created by constructing a multi-behavior line graph, enhancing the global session representation. Finally, the local session representation, global session representation, and global item embedding are used to learn the predicted interaction probability of each item. Extensive experiments are conducted on three real datasets, and the results demonstrate that the proposed model significantly improves recommendation accuracy.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1325-1338"},"PeriodicalIF":8.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-26DOI: 10.1109/TKDE.2024.3522960
Zhida Qin;Wentao Cheng;Wenxing Ding;Gangyi Ding
Hyperbolic space based collaborative filtering has emerged as a popular topic in recommender systems. Compared to the euclidean space, hyperbolic space is more suitable to the tree-like structures in the user-item interactions and can achieve better recommender performance. Although some works have been devoted to this popular topic and made some progresses, they use tangent space as an approximation of hyperbolic space to implement model. Despite the effectiveness, such methods fail to fully exploit the advantages of hyperbolic space and still suffer from the data sparsity issue, which severely limits the recommender performance. To tackle these problems, we refer to the self-supervised learning technique and novelly propose a Hyperbolic Graph Contrastive Learning (HyperCL) framework. Specifically, our framework encodes the augmentation views from both the tangent space and the hyperbolic space, and construct the contrast pairs based on their corresponding learned node representations. Our model not only leverages the geometric advantages of both sides but also achieves seamless information transmission between the two spaces. Extensive experimental results on public benchmark datasets demonstrate that our model is highly competitive and outperforms leading baselines by considerable margins. Further experiments validate the robustness and the superiority of contrastive learning paradigm.
{"title":"Hyperbolic Graph Contrastive Learning for Collaborative Filtering","authors":"Zhida Qin;Wentao Cheng;Wenxing Ding;Gangyi Ding","doi":"10.1109/TKDE.2024.3522960","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3522960","url":null,"abstract":"Hyperbolic space based collaborative filtering has emerged as a popular topic in recommender systems. Compared to the euclidean space, hyperbolic space is more suitable to the tree-like structures in the user-item interactions and can achieve better recommender performance. Although some works have been devoted to this popular topic and made some progresses, they use tangent space as an approximation of hyperbolic space to implement model. Despite the effectiveness, such methods fail to fully exploit the advantages of hyperbolic space and still suffer from the data sparsity issue, which severely limits the recommender performance. To tackle these problems, we refer to the self-supervised learning technique and novelly propose a <bold>Hyper</b>bolic Graph <bold>C</b>ontrastive <bold>L</b>earning (<italic>HyperCL</i>) framework. Specifically, our framework encodes the augmentation views from both the tangent space and the hyperbolic space, and construct the contrast pairs based on their corresponding learned node representations. Our model not only leverages the geometric advantages of both sides but also achieves seamless information transmission between the two spaces. Extensive experimental results on public benchmark datasets demonstrate that our model is highly competitive and outperforms leading baselines by considerable margins. Further experiments validate the robustness and the superiority of contrastive learning paradigm.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1255-1267"},"PeriodicalIF":8.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Class imbalance learning is a challenging task in machine learning applications. To balance training data, traditional class imbalance learning approaches, such as class resampling or reweighting, are commonly applied in the literature. However, these methods can have significant limitations, particularly in the presence of noisy data, missing values, or when applied to advanced learning paradigms like semi-supervised or federated learning. To address these limitations, this paper proposes a novel and theoretically-ensured latent Feature Rectification method for clAss iMbalance lEarning (FRAME). The proposed FRAME can automatically learn multiple centroids for each class in the latent space and then perform class balancing. Unlike data-level methods, FRAME balances feature in the latent space rather than the original space. Compared to algorithm-level methods, FRAME can distinguish different classes based on distance without the need to adjust the learning algorithms. Through latent feature rectification, FRAME can effectively mitigate contaminated noises/missing values without worrying about structural variations in the data. In order to accommodate a wider range of applications, this paper extends FRAME to the following three main learning paradigms: fully-supervised learning, semi-supervised learning, and federated learning. Extensive experiments on 10 binary-class datasets demonstrate that our FRAME can achieve competitive performance than the state-of-the-art methods and its robustness to noises/missing values.
{"title":"FRAME: Feature Rectification for Class Imbalance Learning","authors":"Xu Cheng;Fan Shi;Yao Zhang;Huan Li;Xiufeng Liu;Shengyong Chen","doi":"10.1109/TKDE.2024.3523043","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3523043","url":null,"abstract":"Class imbalance learning is a challenging task in machine learning applications. To balance training data, traditional class imbalance learning approaches, such as class resampling or reweighting, are commonly applied in the literature. However, these methods can have significant limitations, particularly in the presence of noisy data, missing values, or when applied to advanced learning paradigms like semi-supervised or federated learning. To address these limitations, this paper proposes a novel and theoretically-ensured latent <bold>F</b>eature <bold>R</b>ectification method for cl<bold>A</b>ss i<bold>M</b>balance l<bold>E</b>arning (FRAME). The proposed FRAME can automatically learn multiple centroids for each class in the latent space and then perform class balancing. Unlike data-level methods, FRAME balances feature in the latent space rather than the original space. Compared to algorithm-level methods, FRAME can distinguish different classes based on distance without the need to adjust the learning algorithms. Through latent feature rectification, FRAME can effectively mitigate contaminated noises/missing values without worrying about structural variations in the data. In order to accommodate a wider range of applications, this paper extends FRAME to the following three main learning paradigms: fully-supervised learning, semi-supervised learning, and federated learning. Extensive experiments on 10 binary-class datasets demonstrate that our FRAME can achieve competitive performance than the state-of-the-art methods and its robustness to noises/missing values.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1167-1181"},"PeriodicalIF":8.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-26DOI: 10.1109/TKDE.2024.3523107
Chao Fu;Guannan Liu;Kun Yuan;Junjie Wu
Fraud detection has always been one of the primary concerns in social and economic activities and is becoming a decisive force in the booming digital economy. Graph structures formed by rich user interactions naturally serve as important clues for identifying fraudsters. While numerous graph neural network-based methods have been proposed, the diverse interactive connections within graphs and the heterophilic connections deliberately established by fraudsters to normal users as camouflage pose new research challenges. In this light, we propose H2IDE (Homophily and Heterophily Identification with Disentangled Embeddings) for accurate fraud detection in multi-relation graphs. H2IDE features in an independence-constrained disentangled representation learning scheme to capture various latent behavioral patterns in graphs, along with a supervised identification task to specifically model the factor-wise heterophilic connections, both of which are proven crucial to fraud detection. We also design a relation-aware attention mechanism for hierarchical and adaptive neighborhood aggregation in H2IDE. Extensive comparative experiments with state-of-the-art baseline methods on two real-world multi-relation graphs and two large-scale homogeneous graphs demonstrate the superiority and scalability of our proposed method and highlight the key role of disentangled representation learning with homophily and heterophily identification.
{"title":"Nowhere to H2IDE: Fraud Detection From Multi-Relation Graphs via Disentangled Homophily and Heterophily Identification","authors":"Chao Fu;Guannan Liu;Kun Yuan;Junjie Wu","doi":"10.1109/TKDE.2024.3523107","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3523107","url":null,"abstract":"Fraud detection has always been one of the primary concerns in social and economic activities and is becoming a decisive force in the booming digital economy. Graph structures formed by rich user interactions naturally serve as important clues for identifying fraudsters. While numerous graph neural network-based methods have been proposed, the diverse interactive connections within graphs and the heterophilic connections deliberately established by fraudsters to normal users as camouflage pose new research challenges. In this light, we propose H<sup>2</sup>IDE (Homophily and Heterophily Identification with Disentangled Embeddings) for accurate fraud detection in multi-relation graphs. H<sup>2</sup>IDE features in an independence-constrained disentangled representation learning scheme to capture various latent behavioral patterns in graphs, along with a supervised identification task to specifically model the factor-wise heterophilic connections, both of which are proven crucial to fraud detection. We also design a relation-aware attention mechanism for hierarchical and adaptive neighborhood aggregation in H<sup>2</sup>IDE. Extensive comparative experiments with state-of-the-art baseline methods on two real-world multi-relation graphs and two large-scale homogeneous graphs demonstrate the superiority and scalability of our proposed method and highlight the key role of disentangled representation learning with homophily and heterophily identification.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1380-1393"},"PeriodicalIF":8.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-26DOI: 10.1109/TKDE.2024.3523283
Yunfei Yin;Yiming Pan;Xianjian Bao;Faliang Huang
Conversational recommendation is one system that can extract the user's preferences and recommend suitable items in a similar way to human-like responses. Existing methods often use the feature extraction combined with the Transformer model to extract user preferences and make recommendations. However, these methods have two limitations. First, they do not consider the order in which entities appear, thus affecting the extraction of user preferences. Second, the generated responses lack diversity that affects the users’ experience to the system. To this end, we propose a conversational recommendation model with User Entity focus and Multi-Granularity latent variable enhancement (UEMG). In UEMG, we design a novel neural network that utilizes Bi-GRU to capture the appearing orders of entities in dialogues, and leverages Transformer to capture the global dependencies of entities, and then combines them to extract user preferences. For the second issue, to improve the diversity of dialogue generation, we propose a multi-granularity latent variable mechanism, which can extract more entities from the context information and the knowledge graphs, respectively. We conducted extensive experiments on publicly available dialogue generation datasets. Experimental results demonstrate that compared to current state-of-the-art methods, UEMG achieves 9.7% improvements in recommendation performance and 23% improvements in dialogue generation.
{"title":"Conversational Recommendations With User Entity Focus and Multi-Granularity Latent Variable Enhancement","authors":"Yunfei Yin;Yiming Pan;Xianjian Bao;Faliang Huang","doi":"10.1109/TKDE.2024.3523283","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3523283","url":null,"abstract":"Conversational recommendation is one system that can extract the user's preferences and recommend suitable items in a similar way to human-like responses. Existing methods often use the feature extraction combined with the Transformer model to extract user preferences and make recommendations. However, these methods have two limitations. First, they do not consider the order in which entities appear, thus affecting the extraction of user preferences. Second, the generated responses lack diversity that affects the users’ experience to the system. To this end, we propose a conversational recommendation model with User Entity focus and Multi-Granularity latent variable enhancement (UEMG). In UEMG, we design a novel neural network that utilizes Bi-GRU to capture the appearing orders of entities in dialogues, and leverages Transformer to capture the global dependencies of entities, and then combines them to extract user preferences. For the second issue, to improve the diversity of dialogue generation, we propose a multi-granularity latent variable mechanism, which can extract more entities from the context information and the knowledge graphs, respectively. We conducted extensive experiments on publicly available dialogue generation datasets. Experimental results demonstrate that compared to current state-of-the-art methods, UEMG achieves 9.7% improvements in recommendation performance and 23% improvements in dialogue generation.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 3","pages":"1126-1139"},"PeriodicalIF":8.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","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：