Pub Date : 2024-08-20DOI: 10.1109/TKDE.2024.3446584
Fang Wu;Siyuan Li;Stan Z. Li
Graph neural networks (GNNs) rely mainly on the message-passing paradigm to propagate node features and build interactions, and different graph learning problems require different ranges of node interactions. In this work, we explore the capacity of GNNs to capture node interactions under contexts of different complexities. We discover that GNNs usually fail to capture the most informative kinds of interaction styles for diverse graph learning tasks , and thus name this phenomenon as GNNs’ representation bottleneck. As a response, we demonstrate that the inductive bias introduced by existing graph construction mechanisms can result in this representation bottleneck, i.e., preventing GNNs from learning interactions of the most appropriate complexity. To address that limitation, we propose a novel graph rewiring approach based on interaction patterns learned by GNNs to adjust each node's receptive fields dynamically. Extensive experiments on both real-world and synthetic datasets prove the effectiveness of our algorithm in alleviating the representation bottleneck and its superiority in enhancing the performance of GNNs over state-of-the-art graph rewiring baselines.
{"title":"Discovering the Representation Bottleneck of Graph Neural Networks","authors":"Fang Wu;Siyuan Li;Stan Z. Li","doi":"10.1109/TKDE.2024.3446584","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3446584","url":null,"abstract":"Graph neural networks (GNNs) rely mainly on the message-passing paradigm to propagate node features and build interactions, and different graph learning problems require different ranges of node interactions. In this work, we explore the capacity of GNNs to capture node interactions under contexts of different complexities. We discover that \u0000<italic>GNNs usually fail to capture the most informative kinds of interaction styles for diverse graph learning tasks</i>\u0000, and thus name this phenomenon as GNNs’ representation bottleneck. As a response, we demonstrate that the inductive bias introduced by existing graph construction mechanisms can result in this representation bottleneck, i.e., preventing GNNs from learning interactions of the most appropriate complexity. To address that limitation, we propose a novel graph rewiring approach based on interaction patterns learned by GNNs to adjust each node's receptive fields dynamically. Extensive experiments on both real-world and synthetic datasets prove the effectiveness of our algorithm in alleviating the representation bottleneck and its superiority in enhancing the performance of GNNs over state-of-the-art graph rewiring baselines.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7998-8008"},"PeriodicalIF":8.9,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10640313","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Many large-scale machine learning approaches and graph algorithms are proposed recently to address a variety of problems in online social networks (OSNs). To evaluate and validate these algorithms and models, the data of ego-centric networks (ego networks) are widely adopted. Therefore, effectively extracting large-scale ego networks from OSNs becomes an important issue, particularly when privacy policies become increasingly strict nowadays. In this paper, we study the problem of extracting ego network data by considering jointly the user willingness, crawling cost, and structure of the network. We formulate a new research problem, named Structure and Willingness Aware Ego Network Extraction (SWAN) and analyze its NP-hardness. We first propose a $(1-frac{1}{e})$ -approximation algorithm, named Tristar-Optimized Ego Network Identification with Maximum Willingness (TOMW) . In addition to the deterministic approximation algorithm, we also propose to automatically learn an effective heuristic approach with machine learning, to avoid the huge efforts for human to devise a good algorithm. The learning approach is named Willingness-maximized and Structure-aware Ego Network Extraction with Reinforcement Learning (WSRL) , in which we propose a novel constrastive learning strategy, named Contrastive Learning with Performance-boosting Graph Augmentation . We recruited 1,810 real-world participants and conducted an evaluation study to validate our problem formulation and proposed approaches. Moreover, experimental results on real social network datasets show that the proposed approaches outperform the other baselines significantly.
最近提出了许多大规模机器学习方法和图算法，以解决在线社交网络（OSN）中的各种问题。为了评估和验证这些算法和模型，以自我为中心的网络（自我网络）数据被广泛采用。因此，有效地从 OSN 中提取大规模自我网络成为一个重要问题，尤其是在隐私政策日益严格的今天。本文通过综合考虑用户意愿、抓取成本和网络结构，研究了提取自我网络数据的问题。我们提出了一个新的研究问题，命名为 "结构和意愿感知自我网络提取（SWAN）"，并分析了它的 NP 难度。我们首先提出了一种$(1-frac{1}{e})$近似算法，命名为具有最大意愿的三星优化自我网络识别（TOMW）。除了确定性近似算法外，我们还建议利用机器学习自动学习一种有效的启发式方法，以避免人类为设计出一种好算法而付出巨大努力。这种学习方法被命名为 "意愿最大化和结构感知自我网络提取与强化学习（WSRL）"，其中我们提出了一种新颖的对比学习策略，即 "性能提升图增强对比学习（Contrastive Learning with Performance-boosting Graph Augmentation）"。我们招募了 1,810 名真实世界的参与者，并开展了一项评估研究，以验证我们提出的问题和方法。此外，在真实社交网络数据集上的实验结果表明，所提出的方法明显优于其他基线方法。
{"title":"Budget-Constrained Ego Network Extraction With Maximized Willingness","authors":"Bay-Yuan Hsu;Chia-Hsun Lu;Ming-Yi Chang;Chih-Ying Tseng;Chih-Ya Shen","doi":"10.1109/TKDE.2024.3446169","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3446169","url":null,"abstract":"Many large-scale machine learning approaches and graph algorithms are proposed recently to address a variety of problems in online social networks (OSNs). To evaluate and validate these algorithms and models, the data of ego-centric networks (ego networks) are widely adopted. Therefore, effectively extracting large-scale ego networks from OSNs becomes an important issue, particularly when privacy policies become increasingly strict nowadays. In this paper, we study the problem of extracting ego network data by considering jointly the user willingness, crawling cost, and structure of the network. We formulate a new research problem, named \u0000<i>Structure and Willingness Aware Ego Network Extraction (SWAN)</i>\u0000 and analyze its NP-hardness. We first propose a \u0000<inline-formula><tex-math>$(1-frac{1}{e})$</tex-math></inline-formula>\u0000-approximation algorithm, named \u0000<i>Tristar-Optimized Ego Network Identification with Maximum Willingness (TOMW)</i>\u0000. In addition to the deterministic approximation algorithm, we also propose to automatically \u0000<i>learn</i>\u0000 an effective heuristic approach with machine learning, to avoid the huge efforts for human to devise a good algorithm. The learning approach is named \u0000<i>Willingness-maximized and Structure-aware Ego Network Extraction with Reinforcement Learning (WSRL)</i>\u0000, in which we propose a novel constrastive learning strategy, named \u0000<i>Contrastive Learning with Performance-boosting Graph Augmentation</i>\u0000. We recruited 1,810 real-world participants and conducted an evaluation study to validate our problem formulation and proposed approaches. Moreover, experimental results on real social network datasets show that the proposed approaches outperform the other baselines significantly.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7692-7707"},"PeriodicalIF":8.9,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645398","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 : 2024-08-19DOI: 10.1109/TKDE.2024.3438943
Na Wang;Shuxi Xu;Chuan Qin;Sian-Jheng Lin;Shuo Shao;Yunghsiang S. Han
Reversible data hiding (RDH) has been extensively studied in the field of multimedia security. Embedding capacity is an important metric for RDH performance evaluation. However, the embedding capacity of existing methods for independent and identically distributed (i.i.d.) gray-scale signals is still not good enough. In this paper, we propose a high-capacity RDH code construction method that employs asymmetric numeral systems (ANS) coding as the underlying coding framework. Based on the proposed framework, two RDH methods are presented. First, we propose a static RDH method that takes the constant host probability mass function (PMF) as input parameters and offers high embedding performance. Then, we give a dynamic RDH method that can eliminate the need for transmitting the host PMF in advance by designing a reversible dynamic probability calculator. The simulation results on discrete normally distributed signals demonstrate that the performance of the proposed static method is very close to the expected rate-distortion bound, and the proposed dynamic method can achieve satisfactory embedding capacity without prior knowledge of host PMF at the cost of slightly sacrificing steganographic data quality. Moreover, the experimental results on gray-scale images show that the proposed static method provides higher peak signal-to-noise ratio (PSNR) values and larger embedding capacities than some state-of-the-art methods, e.g., the embedding capacity of image Lena is as high as 3.571 bits per pixel.
{"title":"High-Capacity Framework for Reversible Data Hiding Using Asymmetric Numeral Systems","authors":"Na Wang;Shuxi Xu;Chuan Qin;Sian-Jheng Lin;Shuo Shao;Yunghsiang S. Han","doi":"10.1109/TKDE.2024.3438943","DOIUrl":"10.1109/TKDE.2024.3438943","url":null,"abstract":"Reversible data hiding (RDH) has been extensively studied in the field of multimedia security. Embedding capacity is an important metric for RDH performance evaluation. However, the embedding capacity of existing methods for independent and identically distributed (i.i.d.) gray-scale signals is still not good enough. In this paper, we propose a high-capacity RDH code construction method that employs asymmetric numeral systems (ANS) coding as the underlying coding framework. Based on the proposed framework, two RDH methods are presented. First, we propose a static RDH method that takes the constant host probability mass function (PMF) as input parameters and offers high embedding performance. Then, we give a dynamic RDH method that can eliminate the need for transmitting the host PMF in advance by designing a reversible dynamic probability calculator. The simulation results on discrete normally distributed signals demonstrate that the performance of the proposed static method is very close to the expected rate-distortion bound, and the proposed dynamic method can achieve satisfactory embedding capacity without prior knowledge of host PMF at the cost of slightly sacrificing steganographic data quality. Moreover, the experimental results on gray-scale images show that the proposed static method provides higher peak signal-to-noise ratio (PSNR) values and larger embedding capacities than some state-of-the-art methods, e.g., the embedding capacity of image Lena is as high as 3.571 bits per pixel.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"8447-8461"},"PeriodicalIF":8.9,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220123","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 : 2024-08-19DOI: 10.1109/TKDE.2024.3425891
Yankai Chen;Yixiang Fang;Yifei Zhang;Chenhao Ma;Yang Hong;Irwin King
Searching on bipartite graphs serves as a fundamental task for various real-world applications, such as recommendation systems, database retrieval, and document querying. Conventional approaches rely on similarity matching in continuous euclidean space of vectorized node embeddings. To handle intensive similarity computation efficiently, hashing techniques for graph-structured data have emerged as a prominent research direction. However, despite the retrieval efficiency in Hamming space, previous studies have encountered catastrophic performance decay . To address this challenge, we investigate the problem of hashing with Graph Convolutional Network for effective Top-N search. Our findings indicate the learning effectiveness of incorporating hashing techniques within the exploration of bipartite graph reception fields, as opposed to simply treating hashing as post-processing to output embeddings. To further enhance the model performance, we advance upon these findings and propose B ipartite G raph C ontrastive H ashing ( BGCH+ ). BGCH+ introduces a novel dual augmentation approach to both intermediate information and hash code outputs in the latent feature spaces, thereby producing more expressive and robust hash codes within a dual self-supervised learning paradigm. Comprehensive empirical analyses on six real-world benchmarks validate the effectiveness of our dual feature contrastive learning in boosting the performance of BGCH+ compared to existing approaches.
{"title":"Towards Effective Top-N Hamming Search via Bipartite Graph Contrastive Hashing","authors":"Yankai Chen;Yixiang Fang;Yifei Zhang;Chenhao Ma;Yang Hong;Irwin King","doi":"10.1109/TKDE.2024.3425891","DOIUrl":"10.1109/TKDE.2024.3425891","url":null,"abstract":"Searching on bipartite graphs serves as a fundamental task for various real-world applications, such as recommendation systems, database retrieval, and document querying. Conventional approaches rely on similarity matching in continuous euclidean space of vectorized node embeddings. To handle intensive similarity computation efficiently, hashing techniques for graph-structured data have emerged as a prominent research direction. However, despite the retrieval efficiency in Hamming space, previous studies have encountered \u0000<italic>catastrophic performance decay</i>\u0000. To address this challenge, we investigate the problem of hashing with Graph Convolutional Network for effective Top-N search. Our findings indicate the learning effectiveness of incorporating hashing techniques within the exploration of bipartite graph reception fields, as opposed to simply treating hashing as post-processing to output embeddings. To further enhance the model performance, we advance upon these findings and propose \u0000<bold>B</b>\u0000ipartite \u0000<bold>G</b>\u0000raph \u0000<bold>C</b>\u0000ontrastive \u0000<bold>H</b>\u0000ashing (\u0000<bold>BGCH+</b>\u0000). BGCH+ introduces a novel dual augmentation approach to both \u0000<italic>intermediate information</i>\u0000 and \u0000<italic>hash code outputs</i>\u0000 in the latent feature spaces, thereby producing more expressive and robust hash codes within a dual self-supervised learning paradigm. Comprehensive empirical analyses on six real-world benchmarks validate the effectiveness of our dual feature contrastive learning in boosting the performance of BGCH+ compared to existing approaches.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"9418-9432"},"PeriodicalIF":8.9,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10638796","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Instant delivery services, such as food delivery and package delivery, have achieved explosive growth in recent years by providing customers with daily-life convenience. An emerging research area within these services is service Route&Time Prediction (RTP), which aims to estimate the future service route as well as the arrival time of a given worker. As one of the most crucial tasks in those service platforms, RTP stands central to enhancing user satisfaction and trimming operational expenditures on these platforms. Despite a plethora of algorithms developed to date, there is no systematic, comprehensive survey to guide researchers in this domain. To fill this gap, our work presents the first comprehensive survey that methodically categorizes recent advances in service route and time prediction. We start by defining the RTP challenge and then delve into the metrics that are often employed. Following that, we scrutinize the existing RTP methodologies, presenting a novel taxonomy of them. We categorize these methods based on three criteria: (i) type of task, subdivided into only-route prediction, only-time prediction, and joint route&time prediction; (ii) model architecture, which encompasses sequence-based and graph-based models; and (iii) learning paradigm, including Supervised Learning (SL) and Deep Reinforcement Learning (DRL). Conclusively, we highlight the limitations of current research and suggest prospective avenues. We believe that the taxonomy, progress, and prospects introduced in this paper can significantly promote the development of this field.
{"title":"A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects","authors":"Haomin Wen;Youfang Lin;Lixia Wu;Xiaowei Mao;Tianyue Cai;Yunfeng Hou;Shengnan Guo;Yuxuan Liang;Guangyin Jin;Yiji Zhao;Roger Zimmermann;Jieping Ye;Huaiyu Wan","doi":"10.1109/TKDE.2024.3441309","DOIUrl":"10.1109/TKDE.2024.3441309","url":null,"abstract":"Instant delivery services, such as food delivery and package delivery, have achieved explosive growth in recent years by providing customers with daily-life convenience. An emerging research area within these services is service Route&Time Prediction (RTP), which aims to estimate the future service route as well as the arrival time of a given worker. As one of the most crucial tasks in those service platforms, RTP stands central to enhancing user satisfaction and trimming operational expenditures on these platforms. Despite a plethora of algorithms developed to date, there is no systematic, comprehensive survey to guide researchers in this domain. To fill this gap, our work presents the first comprehensive survey that methodically categorizes recent advances in service route and time prediction. We start by defining the RTP challenge and then delve into the metrics that are often employed. Following that, we scrutinize the existing RTP methodologies, presenting a novel taxonomy of them. We categorize these methods based on three criteria: (i) type of task, subdivided into only-route prediction, only-time prediction, and joint route&time prediction; (ii) model architecture, which encompasses sequence-based and graph-based models; and (iii) learning paradigm, including Supervised Learning (SL) and Deep Reinforcement Learning (DRL). Conclusively, we highlight the limitations of current research and suggest prospective avenues. We believe that the taxonomy, progress, and prospects introduced in this paper can significantly promote the development of this field.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7516-7535"},"PeriodicalIF":8.9,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142227344","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}
In this paper, we present the design and implementation of ZBTree, a hotness-aware B $^+$ -Tree for persistent memory (PMem). ZBTree leverages the PMem+DRAM architecture, which is featured with a volatile operation layer to accelerate data access and an order-preserving persistent layer to achieve fast recovery and low-overhead consistency and persistence guarantees. The operation layer contains inner nodes for indexing and compacted leaf nodes (DLeaves) that hold metadata. Based on leaf node compaction, we present a data lodging method, which supports to load hot data into fast DRAM dynamically, avoiding PMem accesses for subsequent reads of hot data and achieving improved read performance without incurring extra DRAM usage. In addition, we present a lightweight node splitting mechanism with constant persistence overhead that does not vary with node size. Our extensive evaluations show that ZBTree achieves higher throughput by a factor of 1.4x-6.3x compared to state-of-the-art tree indexes under a wide range of workloads. Meanwhile, ZBTree achieves comparable or faster recovery speed compared to existing designs.
在本文中，我们介绍了 ZBTree 的设计与实现，这是一种用于持久内存（PMem）的热感知 B$^+$ 树。ZBTree 利用 PMem+DRAM 架构，该架构具有易失性操作层和保序持久层，易失性操作层用于加速数据访问，保序持久层用于实现快速恢复以及低开销的一致性和持久性保证。操作层包含用于索引的内部节点和保存元数据的压缩叶节点（DLeaves）。在叶节点压缩的基础上，我们提出了一种数据寄存方法，它支持将热数据动态加载到快速 DRAM 中，从而避免了后续读取热数据时对 PMem 的访问，并在不占用额外 DRAM 的情况下提高了读取性能。此外，我们还提出了一种轻量级节点拆分机制，该机制具有恒定的持久性开销，不会随节点大小而变化。我们的广泛评估表明，在各种工作负载下，ZBTree 的吞吐量比最先进的树索引高出 1.4-6.3 倍。同时，与现有设计相比，ZBTree 的恢复速度相当或更快。
{"title":"ZBTree: A Fast and Scalable B$^+$+-Tree for Persistent Memory","authors":"Wenkui Che;Zhiwen Chen;Daokun Hu;Jianhua Sun;Hao Chen","doi":"10.1109/TKDE.2024.3421232","DOIUrl":"10.1109/TKDE.2024.3421232","url":null,"abstract":"In this paper, we present the design and implementation of ZBTree, a hotness-aware B\u0000<inline-formula><tex-math>$^+$</tex-math></inline-formula>\u0000-Tree for persistent memory (PMem). ZBTree leverages the PMem+DRAM architecture, which is featured with a volatile operation layer to accelerate data access and an order-preserving persistent layer to achieve fast recovery and low-overhead consistency and persistence guarantees. The operation layer contains inner nodes for indexing and compacted leaf nodes (DLeaves) that hold metadata. Based on leaf node compaction, we present a data lodging method, which supports to load hot data into fast DRAM dynamically, avoiding PMem accesses for subsequent reads of hot data and achieving improved read performance without incurring extra DRAM usage. In addition, we present a lightweight node splitting mechanism with constant persistence overhead that does not vary with node size. Our extensive evaluations show that ZBTree achieves higher throughput by a factor of 1.4x-6.3x compared to state-of-the-art tree indexes under a wide range of workloads. Meanwhile, ZBTree achieves comparable or faster recovery speed compared to existing designs.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"9547-9563"},"PeriodicalIF":8.9,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220129","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}
Forecasting financial data plays a crucial role in financial market. Relying solely on prices or price trends as prediction targets often leads to a vast of invalid transactions. As a result, researchers have increasingly turned their attention to turning points as the prediction target. Surprisingly, existing methods have largely overlooked the role of technical charts, despite turning points being closely related to the technical charts. Recently, several researchers have attempted to utilize chart information via converting price sequences into images for turning point forecasting, but robustness and convergence problems arise. To address these challenges and enhance the turning point predictions, this article introduces a new method known as MPCNet. Specifically, we first transform the price series into a graph structure using chart similarity to robustly extract valuable information from technical charts. Additionally, we introduce the multipersistence topology tool to accurately predict stock turning points and provide convergence guarantee. Experimental results demonstrate the significant superiority of our proposed model over existing methods. Furthermore, based on additional performance evaluations using real stock data, MPCNet consistently achieves the highest average return during the transaction backtesting period. Meanwhile, we provide empirical validation of robustness and theoretical analysis to confirm its convergence, establishing it as a superior tool for financial forecasting.
{"title":"Forecasting Turning Points in Stock Price by Integrating Chart Similarity and Multipersistence","authors":"Shangzhe Li;Yingke Liu;Xueyuan Chen;Junran Wu;Ke Xu","doi":"10.1109/TKDE.2024.3444814","DOIUrl":"10.1109/TKDE.2024.3444814","url":null,"abstract":"Forecasting financial data plays a crucial role in financial market. Relying solely on prices or price trends as prediction targets often leads to a vast of invalid transactions. As a result, researchers have increasingly turned their attention to turning points as the prediction target. Surprisingly, existing methods have largely overlooked the role of technical charts, despite turning points being closely related to the technical charts. Recently, several researchers have attempted to utilize chart information via converting price sequences into images for turning point forecasting, but robustness and convergence problems arise. To address these challenges and enhance the turning point predictions, this article introduces a new method known as MPCNet. Specifically, we first transform the price series into a graph structure using chart similarity to robustly extract valuable information from technical charts. Additionally, we introduce the multipersistence topology tool to accurately predict stock turning points and provide convergence guarantee. Experimental results demonstrate the significant superiority of our proposed model over existing methods. Furthermore, based on additional performance evaluations using real stock data, MPCNet consistently achieves the highest average return during the transaction backtesting period. Meanwhile, we provide empirical validation of robustness and theoretical analysis to confirm its convergence, establishing it as a superior tool for financial forecasting.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"8251-8266"},"PeriodicalIF":8.9,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220127","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 : 2024-08-15DOI: 10.1109/TKDE.2024.3443888
Weiping Ding;Xiaotian Cheng;Yu Geng;Jiashuang Huang;Hengrong Ju
Transformer interpretability research is a hot topic in the area of deep learning. Traditional interpretation methods mostly use the final layer output of the Transformer encoder as masks to generate an explanation map. However, These approaches overlook two crucial aspects. At the coarse-grained level, the mask may contain uncertain information, including unreliable and incomplete object location data; at the fine-grained level, there is information loss on the mask, resulting in spatial noise and detail loss. To address these issues, in this paper, we propose a two-stage coarse-to-fine strategy (C2F-Explainer) for improving Transformer interpretability. Specifically, we first design a sequential three-way mask (S3WM) module to handle the problem of uncertain information at the coarse-grained level. This module uses sequential three-way decisions to process the mask, preventing uncertain information on the mask from impacting the interpretation results, thus obtaining coarse-grained interpretation results with accurate position. Second, to further reduce the impact of information loss at the fine-grained level, we devised an attention fusion (AF) module inspired by the fact that self-attention can capture global semantic information, AF aggregates the attention matrix to generate a cross-layer relation matrix, which is then used to optimize detailed information on the interpretation results and produce fine-grained interpretation results with clear and complete edges. Experimental results show that the proposed C2F-Explainer has good interpretation results on both natural and medical image datasets, and the mIoU is improved by 2.08% on the PASCAL VOC 2012 dataset.
{"title":"C2F-Explainer: Explaining Transformers Better Through a Coarse-to-Fine Strategy","authors":"Weiping Ding;Xiaotian Cheng;Yu Geng;Jiashuang Huang;Hengrong Ju","doi":"10.1109/TKDE.2024.3443888","DOIUrl":"10.1109/TKDE.2024.3443888","url":null,"abstract":"Transformer interpretability research is a hot topic in the area of deep learning. Traditional interpretation methods mostly use the final layer output of the Transformer encoder as masks to generate an explanation map. However, These approaches overlook two crucial aspects. At the coarse-grained level, the mask may contain uncertain information, including unreliable and incomplete object location data; at the fine-grained level, there is information loss on the mask, resulting in spatial noise and detail loss. To address these issues, in this paper, we propose a two-stage coarse-to-fine strategy (C2F-Explainer) for improving Transformer interpretability. Specifically, we first design a sequential three-way mask (S3WM) module to handle the problem of uncertain information at the coarse-grained level. This module uses sequential three-way decisions to process the mask, preventing uncertain information on the mask from impacting the interpretation results, thus obtaining coarse-grained interpretation results with accurate position. Second, to further reduce the impact of information loss at the fine-grained level, we devised an attention fusion (AF) module inspired by the fact that self-attention can capture global semantic information, AF aggregates the attention matrix to generate a cross-layer relation matrix, which is then used to optimize detailed information on the interpretation results and produce fine-grained interpretation results with clear and complete edges. Experimental results show that the proposed C2F-Explainer has good interpretation results on both natural and medical image datasets, and the mIoU is improved by 2.08% on the PASCAL VOC 2012 dataset.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7708-7724"},"PeriodicalIF":8.9,"publicationDate":"2024-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220130","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 : 2024-08-15DOI: 10.1109/TKDE.2024.3443997
Fuyuan Cao;Yunxia Wang;Kui Yu;Jiye Liang
Inferring causal structures from experimentation is a challenging task in many fields. Most causal structure learning algorithms with unknown interventions are proposed to discover causal relationships over an identical variable set. However, often due to privacy, ethical, financial, and practical concerns, the variable sets observed by multiple sources or domains are not entirely identical. While a few algorithms are proposed to handle the partially overlapping variable sets, they focus on the case of known intervention targets. Therefore, to be close to the real-world environment, we consider discovering causal relationships over overlapping variable sets under the unknown intervention setting and exploring a scenario where a problem is studied across multiple domains. Here, we propose an algorithm for discovering the causal relationships over the integrated set of variables from unknown interventions, mainly handling the entangled inconsistencies caused by the incomplete observation of variables and unknown intervention targets. Specifically, we first distinguish two types of inconsistencies and then deal with respectively them by presenting some lemmas. Finally, we construct a fusion rule to combine learned structures of multiple domains, obtaining the final structures over the integrated set of variables. Theoretical analysis and experimental results on synthetic, benchmark, and real-world datasets have verified the effectiveness of the proposed algorithm.
{"title":"Causal Discovery From Unknown Interventional Datasets Over Overlapping Variable Sets","authors":"Fuyuan Cao;Yunxia Wang;Kui Yu;Jiye Liang","doi":"10.1109/TKDE.2024.3443997","DOIUrl":"10.1109/TKDE.2024.3443997","url":null,"abstract":"Inferring causal structures from experimentation is a challenging task in many fields. Most causal structure learning algorithms with unknown interventions are proposed to discover causal relationships over an identical variable set. However, often due to privacy, ethical, financial, and practical concerns, the variable sets observed by multiple sources or domains are not entirely identical. While a few algorithms are proposed to handle the partially overlapping variable sets, they focus on the case of known intervention targets. Therefore, to be close to the real-world environment, we consider discovering causal relationships over overlapping variable sets under the unknown intervention setting and exploring a scenario where a problem is studied across multiple domains. Here, we propose an algorithm for discovering the causal relationships over the integrated set of variables from unknown interventions, mainly handling the entangled inconsistencies caused by the incomplete observation of variables and unknown intervention targets. Specifically, we first distinguish two types of inconsistencies and then deal with respectively them by presenting some lemmas. Finally, we construct a fusion rule to combine learned structures of multiple domains, obtaining the final structures over the integrated set of variables. Theoretical analysis and experimental results on synthetic, benchmark, and real-world datasets have verified the effectiveness of the proposed algorithm.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7725-7742"},"PeriodicalIF":8.9,"publicationDate":"2024-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220128","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：