Pub Date : 2023-07-11DOI: 10.1109/TETC.2023.3292384
Guan Wang;Weihua Li;Quan Bai;Edmund M-K Lai
With the rapid advancement of the Internet and social platforms, how to maximize the influence across popular online social networks has attracted great attention from both researchers and practitioners. Almost all the existing influence diffusion models assume that influence remains constant in the process of information spreading. However, in the real world, people tend to alternate information by attaching opinions or modifying the contents before spreading it. Namely, the meaning and idea of a message normally mutate in the process of influence diffusion. In this article, we investigate how to maximize the influence in online social platforms with a key consideration of suppressing the information alteration in the diffusion cascading process. We leverage deep learning models and knowledge graphs to present users’ personalised behaviours, i.e., actions after receiving a message. Furthermore, we investigate the information alteration in the process of influence diffusion. A novel seed selection algorithm is proposed to maximize the social influence without causing significant information alteration. Experimental results explicitly show the rationale of the proposed user behaviours deep learning model architecture and demonstrate the novel seeding algorithm's outstanding performance in both maximizing influence and retaining the influence originality.
{"title":"Maximizing Social Influence With Minimum Information Alteration","authors":"Guan Wang;Weihua Li;Quan Bai;Edmund M-K Lai","doi":"10.1109/TETC.2023.3292384","DOIUrl":"10.1109/TETC.2023.3292384","url":null,"abstract":"With the rapid advancement of the Internet and social platforms, how to maximize the influence across popular online social networks has attracted great attention from both researchers and practitioners. Almost all the existing influence diffusion models assume that influence remains constant in the process of information spreading. However, in the real world, people tend to alternate information by attaching opinions or modifying the contents before spreading it. Namely, the meaning and idea of a message normally mutate in the process of influence diffusion. In this article, we investigate how to maximize the influence in online social platforms with a key consideration of suppressing the information alteration in the diffusion cascading process. We leverage deep learning models and knowledge graphs to present users’ personalised behaviours, i.e., actions after receiving a message. Furthermore, we investigate the information alteration in the process of influence diffusion. A novel seed selection algorithm is proposed to maximize the social influence without causing significant information alteration. Experimental results explicitly show the rationale of the proposed user behaviours deep learning model architecture and demonstrate the novel seeding algorithm's outstanding performance in both maximizing influence and retaining the influence originality.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":null,"pages":null},"PeriodicalIF":5.9,"publicationDate":"2023-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62528854","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 : 2023-07-11DOI: 10.1109/TETC.2023.3292240
Yong-Min Shin;Cong Tran;Won-Yong Shin;Xin Cao
We study the problem of embedding edgeless nodes such as users who newly enter the underlying network, while using graph neural networks (GNNs) widely studied for effective representation learning of graphs. Our study is motivated by the fact that GNNs cannot be straightforwardly adopted for our problem since message passing to such edgeless nodes having no connections is impossible. To tackle this challenge, we propose $mathsf{Edgeless-GNN}$ , a novel inductive framework that enables GNNs to generate node embeddings even for edgeless nodes through unsupervised learning . Specifically, we start by constructing a proxy graph based on the similarity of node attributes as the GNN's computation graph defined by the underlying network. The known network structure is used to train model parameters, whereas a topology-aware loss function is established such that our model judiciously learns the network structure by encoding positive, negative, and second-order relations between nodes. For the edgeless nodes, we inductively infer embeddings by expanding the computation graph. By evaluating the performance of various downstream machine learning tasks, we empirically demonstrate that $mathsf{Edgeless-GNN}$ exhibits (a) superiority over state-of-the-art inductive network embedding methods for edgeless nodes, (b) effectiveness of our topology-aware loss function, (c) robustness to incomplete node attributes, and (d) a linear scaling with the graph size.
{"title":"Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes","authors":"Yong-Min Shin;Cong Tran;Won-Yong Shin;Xin Cao","doi":"10.1109/TETC.2023.3292240","DOIUrl":"10.1109/TETC.2023.3292240","url":null,"abstract":"We study the problem of embedding \u0000<i>edgeless</i>\u0000 nodes such as users who newly enter the underlying network, while using graph neural networks (GNNs) widely studied for effective representation learning of graphs. Our study is motivated by the fact that GNNs cannot be straightforwardly adopted for our problem since message passing to such edgeless nodes having no connections is impossible. To tackle this challenge, we propose \u0000<inline-formula><tex-math>$mathsf{Edgeless-GNN}$</tex-math></inline-formula>\u0000, a novel inductive framework that enables GNNs to generate node embeddings even for edgeless nodes through \u0000<i>unsupervised learning</i>\u0000. Specifically, we start by constructing a proxy graph based on the similarity of node attributes as the GNN's computation graph defined by the underlying network. The known network structure is used to train model parameters, whereas a \u0000<i>topology-aware</i>\u0000 loss function is established such that our model judiciously learns the network structure by encoding positive, negative, and second-order relations between nodes. For the edgeless nodes, we \u0000<i>inductively</i>\u0000 infer embeddings by expanding the computation graph. By evaluating the performance of various downstream machine learning tasks, we empirically demonstrate that \u0000<inline-formula><tex-math>$mathsf{Edgeless-GNN}$</tex-math></inline-formula>\u0000 exhibits (a) superiority over state-of-the-art inductive network embedding methods for edgeless nodes, (b) effectiveness of our topology-aware loss function, (c) robustness to incomplete node attributes, and (d) a linear scaling with the graph size.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":null,"pages":null},"PeriodicalIF":5.9,"publicationDate":"2023-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44628489","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 : 2023-07-11DOI: 10.1109/TETC.2023.3292355
Takahiro Ohyama;Yuichi Kawamoto;Nei Kato
Intelligent reflecting surfaces (IRSs) have attracted attention as a technology that can considerably improve the energy utilization efficiency of sixth-generation (6G) mobile communication systems. IRSs enable control of propagation characteristics by adjusting the phase shift of each reflective element. However, designing the phase shift requires the acquisition of channel information for each reflective element, which is impractical from an overhead perspective. In addition, for multiple wireless network operators to share an IRS for communication, new infrastructure facilities and operational costs are required at each operator's end to control the IRS in a coordinated manner. Herein, we propose a wireless communication system using standalone IRSs to solve these problems. The standalone IRSs cover a wide area by periodically switching phase shifts, and each operator allocates radio resources according to their phase-shift switching. Furthermore, we derive a quadratic unconstrained binary optimization equation for the proposed system to optimize radio resource allocation using quantum computing. The results of computer simulations indicate that the proposed system and method can be used to achieve efficient communication in 6G mobile communication systems.
{"title":"Resource Allocation Optimization by Quantum Computing for Shared Use of Standalone IRS","authors":"Takahiro Ohyama;Yuichi Kawamoto;Nei Kato","doi":"10.1109/TETC.2023.3292355","DOIUrl":"10.1109/TETC.2023.3292355","url":null,"abstract":"Intelligent reflecting surfaces (IRSs) have attracted attention as a technology that can considerably improve the energy utilization efficiency of sixth-generation (6G) mobile communication systems. IRSs enable control of propagation characteristics by adjusting the phase shift of each reflective element. However, designing the phase shift requires the acquisition of channel information for each reflective element, which is impractical from an overhead perspective. In addition, for multiple wireless network operators to share an IRS for communication, new infrastructure facilities and operational costs are required at each operator's end to control the IRS in a coordinated manner. Herein, we propose a wireless communication system using standalone IRSs to solve these problems. The standalone IRSs cover a wide area by periodically switching phase shifts, and each operator allocates radio resources according to their phase-shift switching. Furthermore, we derive a quadratic unconstrained binary optimization equation for the proposed system to optimize radio resource allocation using quantum computing. The results of computer simulations indicate that the proposed system and method can be used to achieve efficient communication in 6G mobile communication systems.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":null,"pages":null},"PeriodicalIF":5.9,"publicationDate":"2023-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62528843","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}
Convolutional Neural Network (CNN) is used in many real-world applications due to its high accuracy. The rapid growth of modern applications based on learning algorithms has increased the importance of efficient implementation of CNNs. The array-type architecture is a well-known platform for the efficient implementation of CNN models, which takes advantage of parallel computation and data reuse. However, accelerators suffer from restricted hardware resources, whereas CNNs involve considerable communication and computation load. Furthermore, since accelerators execute CNN layer by layer, different shapes and sizes of layers lead to suboptimal resource utilization. This problem prevents the accelerator from reaching maximum performance. The increasing scale and complexity of deep learning applications exacerbate this problem. Therefore, the performance of CNN models depends on the hardware's ability to adapt to different shapes of different layers to increase resource utilization. This work proposes a reconfigurable accelerator that can efficiently execute a wide range of CNNs. The proposed flexible and low-cost reconfigurable interconnect units allow the array to perform CNN faster than fixed-size implementations (by 45.9% for ResNet-18 compared to the baseline). The proposed architecture also reduces the on-chip memory access rate by 36.5% without compromising accuracy.
{"title":"Rei: A Reconfigurable Interconnection Unit for Array-Based CNN Accelerators","authors":"Paria Darbani;Hakem Beitollahi;Pejman Lotfi-Kamran","doi":"10.1109/TETC.2023.3290138","DOIUrl":"10.1109/TETC.2023.3290138","url":null,"abstract":"Convolutional Neural Network (CNN) is used in many real-world applications due to its high accuracy. The rapid growth of modern applications based on learning algorithms has increased the importance of efficient implementation of CNNs. The array-type architecture is a well-known platform for the efficient implementation of CNN models, which takes advantage of parallel computation and data reuse. However, accelerators suffer from restricted hardware resources, whereas CNNs involve considerable communication and computation load. Furthermore, since accelerators execute CNN layer by layer, different shapes and sizes of layers lead to suboptimal resource utilization. This problem prevents the accelerator from reaching maximum performance. The increasing scale and complexity of deep learning applications exacerbate this problem. Therefore, the performance of CNN models depends on the hardware's ability to adapt to different shapes of different layers to increase resource utilization. This work proposes a reconfigurable accelerator that can efficiently execute a wide range of CNNs. The proposed flexible and low-cost reconfigurable interconnect units allow the array to perform CNN faster than fixed-size implementations (by 45.9% for ResNet-18 compared to the baseline). The proposed architecture also reduces the on-chip memory access rate by 36.5% without compromising accuracy.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":null,"pages":null},"PeriodicalIF":5.9,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62528290","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 : 2023-06-30DOI: 10.1109/TETC.2023.3289778
A. Alper Goksoy;Guihong Li;Sumit K. Mandal;Umit Y. Ogras;Radu Marculescu
Sparse deep neural networks (DNNs) have the potential to deliver compelling performance and energy efficiency without significant accuracy loss. However, their benefits can quickly diminish if their training is oblivious to the target hardware. For example, fewer critical connections can have a significant overhead if they translate into long-distance communication on the target hardware. Therefore, hardware-aware sparse training is needed to leverage the full potential of sparse DNNs. To this end, we propose a novel and comprehensive communication-aware sparse DNN optimization framework for tile-based in-memory computing (IMC) architectures. The proposed technique, CANNON first maps the DNN layers onto the tiles of the target architecture. Then, it replaces the fully connected and convolutional layers with communication-aware sparse connections. After that, CANNON optimizes the communication cost with minimal impact on the DNN accuracy. Extensive experimental evaluations with a wide range of DNNs and datasets show up to 3.0× lower communication energy, 3.1× lower communication latency, and 6.8× lower energy-delay product compared to state-of-the-art pruning approaches with a negligible impact on the classification accuracy on IMC-based machine learning accelerators.
{"title":"CANNON: Communication-Aware Sparse Neural Network Optimization","authors":"A. Alper Goksoy;Guihong Li;Sumit K. Mandal;Umit Y. Ogras;Radu Marculescu","doi":"10.1109/TETC.2023.3289778","DOIUrl":"10.1109/TETC.2023.3289778","url":null,"abstract":"Sparse deep neural networks (DNNs) have the potential to deliver compelling performance and energy efficiency without significant accuracy loss. However, their benefits can quickly diminish if their training is oblivious to the target hardware. For example, fewer critical connections can have a significant overhead if they translate into long-distance communication on the target hardware. Therefore, hardware-aware sparse training is needed to leverage the full potential of sparse DNNs. To this end, we propose a novel and comprehensive communication-aware sparse DNN optimization framework for tile-based in-memory computing (IMC) architectures. The proposed technique, CANNON first maps the DNN layers onto the tiles of the target architecture. Then, it replaces the fully connected and convolutional layers with communication-aware sparse connections. After that, CANNON optimizes the communication cost with minimal impact on the DNN accuracy. Extensive experimental evaluations with a wide range of DNNs and datasets show up to 3.0× lower communication energy, 3.1× lower communication latency, and 6.8× lower energy-delay product compared to state-of-the-art pruning approaches with a negligible impact on the classification accuracy on IMC-based machine learning accelerators.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":null,"pages":null},"PeriodicalIF":5.9,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62528280","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 : 2023-06-20DOI: 10.1109/TETC.2023.3286404
Libing Wu;Youhua Xia;Shuwen Min;Zhenchang Xia
Collaborative filtering (CF) is a pivotal building block in commercial recommender systems due to its strength and utility in user interest modeling. Recently, many researchers have turned to deep learning as a way to capture richer collaborative signals from user-item feature interactions. However, most deep-based methods only consider nonlinear, high-order interactions while ignoring the explicit collaborative signals in low-order interactions. They also typically ignore the quality of the user and item profiles. These are cornerstones in item recommendation that, we argue, must be considered for high-quality recommendations. Hence, we propose Deep Attentive Interest Collaborative Filtering (DAICF) to overcome these limitations. DAICF profiles users based on their interactive items, i.e., user neighborhood information. Similarly, item profiles are based on users who had interacted with it, i.e., item neighborhood information. Given a user's profile varies over different items, DAICF accurately models his attentive interests based on the specific target item. Low-order collaborative signals are captured by a shallow component, and high-order collaborative signals are captured by a deep component. These two complementary collaborative signals are then fused to provide rich recommendations that cut through today's information overload. By designing a personalized feature extraction method based on bilateral neighborhood information to solve the data sparsity problem in recommender systems, DAICF can dynamically distinguish the importance of a user's historical interaction items for predicting user preferences for a specific target item. A set of experiments against four real-world datasets validate that DAICF outperforms the most recent state-of-the-art recommendation algorithms and justifies the effectiveness and interpretability of our method.
{"title":"Deep Attentive Interest Collaborative Filtering for Recommender Systems","authors":"Libing Wu;Youhua Xia;Shuwen Min;Zhenchang Xia","doi":"10.1109/TETC.2023.3286404","DOIUrl":"10.1109/TETC.2023.3286404","url":null,"abstract":"Collaborative filtering (CF) is a pivotal building block in commercial recommender systems due to its strength and utility in user interest modeling. Recently, many researchers have turned to deep learning as a way to capture richer collaborative signals from user-item feature interactions. However, most deep-based methods only consider nonlinear, high-order interactions while ignoring the explicit collaborative signals in low-order interactions. They also typically ignore the quality of the user and item profiles. These are cornerstones in item recommendation that, we argue, must be considered for high-quality recommendations. Hence, we propose Deep Attentive Interest Collaborative Filtering (DAICF) to overcome these limitations. DAICF profiles users based on their interactive items, i.e., user neighborhood information. Similarly, item profiles are based on users who had interacted with it, i.e., item neighborhood information. Given a user's profile varies over different items, DAICF accurately models his attentive interests based on the specific target item. Low-order collaborative signals are captured by a shallow component, and high-order collaborative signals are captured by a deep component. These two complementary collaborative signals are then fused to provide rich recommendations that cut through today's information overload. By designing a personalized feature extraction method based on bilateral neighborhood information to solve the data sparsity problem in recommender systems, DAICF can dynamically distinguish the importance of a user's historical interaction items for predicting user preferences for a specific target item. A set of experiments against four real-world datasets validate that DAICF outperforms the most recent state-of-the-art recommendation algorithms and justifies the effectiveness and interpretability of our method.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":null,"pages":null},"PeriodicalIF":5.9,"publicationDate":"2023-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62528714","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 work, a high-speed and energy-efficient comparator-based N ear- S ensor L ocal B inary P attern accelerator architecture (NS-LBP) is proposed to execute a novel local binary pattern deep neural network. First, inspired by recent LBP networks, we design an approximate, hardware-oriented, and multiply-accumulate (MAC)-free network named Ap-LBP for efficient feature extraction, further reducing the computation complexity. Then, we develop NS-LBP as a processing-in-SRAM unit and a parallel in-memory LBP algorithm to process images near the sensor in a cache, remarkably reducing the power consumption of data transmission to an off-chip processor. Our circuit-to-application co-simulation results on MNIST and SVHN datasets demonstrate minor accuracy degradation compared to baseline CNN and LBP-network models, while NS-LBP achieves 1.25 GHz and an energy-efficiency of 37.4 TOPS/W. NS-LBP reduces energy consumption by 2.2× and execution time by a factor of 4× compared to the best recent LBP-based networks.
{"title":"A Near-Sensor Processing Accelerator for Approximate Local Binary Pattern Networks","authors":"Shaahin Angizi;Mehrdad Morsali;Sepehr Tabrizchi;Arman Roohi","doi":"10.1109/TETC.2023.3285493","DOIUrl":"https://doi.org/10.1109/TETC.2023.3285493","url":null,"abstract":"In this work, a high-speed and energy-efficient comparator-based \u0000<underline>N</u>\u0000ear-\u0000<underline>S</u>\u0000ensor \u0000<underline>L</u>\u0000ocal \u0000<underline>B</u>\u0000inary \u0000<underline>P</u>\u0000attern accelerator architecture (NS-LBP) is proposed to execute a novel local binary pattern deep neural network. First, inspired by recent LBP networks, we design an approximate, hardware-oriented, and multiply-accumulate (MAC)-free network named Ap-LBP for efficient feature extraction, further reducing the computation complexity. Then, we develop NS-LBP as a processing-in-SRAM unit and a parallel in-memory LBP algorithm to process images near the sensor in a cache, remarkably reducing the power consumption of data transmission to an off-chip processor. Our circuit-to-application co-simulation results on MNIST and SVHN datasets demonstrate minor accuracy degradation compared to baseline CNN and LBP-network models, while NS-LBP achieves 1.25 GHz and an energy-efficiency of 37.4 TOPS/W. NS-LBP reduces energy consumption by 2.2× and execution time by a factor of 4× compared to the best recent LBP-based networks.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":null,"pages":null},"PeriodicalIF":5.9,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140161150","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 : 2023-06-08DOI: 10.1109/TETC.2023.3282539
Binon Teji;Swarup Roy;Devendra Singh Dhami;Dinabandhu Bhandari;Pietro Hiram Guzzi
Network science tries to understand the complex relationships among entities or actors of a system through graph formalism. For instance, biological networks represent macromolecules such as genes, proteins, or other small chemicals as nodes and the interactions among the molecules as links or edges. Often potential links are guessed computationally due to the expensive nature of wet lab experiments. Conventional link prediction techniques rely on local network topology and fail to incorporate the global structure fully. Graph representation learning (or embedding) aims to describe the properties of the entire graph by optimized, structure-preserving encoding of nodes or entire (sub) graphs into lower-dimensional vectors. Leveraging the encoded vectors as a feature improves the performance of the missing link identification task. Assessing the predictive quality of graph embedding techniques in missing link identification is essential. In this work, we evaluate the performance of ten (10) state-of-the-art graph embedding techniques in predicting missing links with special emphasis on homogeneous and heterogeneous biological networks. Most available graph embedding techniques cannot be used directly for link prediction. Hence, we use the latent representation of the network produced by the candidate techniques and reconstruct the network using various similarity and kernel functions. We evaluate nine (09) similarity functions in combination with candidate embedding techniques. We compare embedding techniques’ performance against five (05) traditional (non-embedding-based) link prediction techniques. Experimental results reveal that the quality of embedding-based link prediction is better than its counterpart. Among them, Neural Network-based embedding and attention-based techniques show consistent performance. We even observe that dot-product-based similarity is the best in inferring pair-wise edges among the nodes from their embedding. We report interesting findings that while predicting links in the heterogeneous graph, it predicts a good number of valid links between corresponding homogeneous nodes due to the possible indirect effect of homogeneous-heterogeneous interactions.
{"title":"Graph Embedding Techniques for Predicting Missing Links in Biological Networks: An Empirical Evaluation","authors":"Binon Teji;Swarup Roy;Devendra Singh Dhami;Dinabandhu Bhandari;Pietro Hiram Guzzi","doi":"10.1109/TETC.2023.3282539","DOIUrl":"10.1109/TETC.2023.3282539","url":null,"abstract":"Network science tries to understand the complex relationships among entities or actors of a system through graph formalism. For instance, biological networks represent macromolecules such as genes, proteins, or other small chemicals as nodes and the interactions among the molecules as links or edges. Often potential links are guessed computationally due to the expensive nature of wet lab experiments. Conventional link prediction techniques rely on local network topology and fail to incorporate the global structure fully. Graph representation learning (or embedding) aims to describe the properties of the entire graph by optimized, structure-preserving encoding of nodes or entire (sub) graphs into lower-dimensional vectors. Leveraging the encoded vectors as a feature improves the performance of the missing link identification task. Assessing the predictive quality of graph embedding techniques in missing link identification is essential. In this work, we evaluate the performance of ten (10) state-of-the-art graph embedding techniques in predicting missing links with special emphasis on homogeneous and heterogeneous biological networks. Most available graph embedding techniques cannot be used directly for link prediction. Hence, we use the latent representation of the network produced by the candidate techniques and reconstruct the network using various similarity and kernel functions. We evaluate nine (09) similarity functions in combination with candidate embedding techniques. We compare embedding techniques’ performance against five (05) traditional (non-embedding-based) link prediction techniques. Experimental results reveal that the quality of embedding-based link prediction is better than its counterpart. Among them, Neural Network-based embedding and attention-based techniques show consistent performance. We even observe that dot-product-based similarity is the best in inferring pair-wise edges among the nodes from their embedding. We report interesting findings that while predicting links in the heterogeneous graph, it predicts a good number of valid links between corresponding homogeneous nodes due to the possible indirect effect of homogeneous-heterogeneous interactions.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":null,"pages":null},"PeriodicalIF":5.9,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62528657","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 : 2023-06-06DOI: 10.1109/TETC.2023.3279759
{"title":"IEEE Transactions on Emerging Topics in Computing Information for Authors","authors":"","doi":"10.1109/TETC.2023.3279759","DOIUrl":"https://doi.org/10.1109/TETC.2023.3279759","url":null,"abstract":"","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":null,"pages":null},"PeriodicalIF":5.9,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/6245516/10144811/10144701.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67883147","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}
Pub Date : 2023-06-06DOI: 10.1109/TETC.2023.3267909
Yuan-Hao Chang;Vincenzo Piuri
The von Neumann architecture has been the status quo since the dawn of modern computing. Computers built on the von Neumann architecture are composed of an intelligent master processor (e.g., CPU) and dumb memory/storage devices incapable of computation (e.g., memory and disk). However, the skyrocketing data volume in modern computing is calling such status quo into question. The excessive amounts of data movement between processor and memory/storage in more and more real-world applications (e.g., machine learning and AI applications) have made the processor-centric design a severe power and performance bottleneck. The diminishing Moore's Law also raises the need for a memory-centric design, which is rising on top of the recent material advancement and manufacturing innovation to open a paradigm shift. By doing computation right inside or near the memory, the memory-centric design promises massive throughput and energy savings.
{"title":"Guest Editorial: IEEE Transactions on Emerging Topics in Computing Thematic Section on Memory- Centric Designs: Processing-in-Memory, In-Memory Computing, and Near-Memory Computing for Real-World Applications","authors":"Yuan-Hao Chang;Vincenzo Piuri","doi":"10.1109/TETC.2023.3267909","DOIUrl":"https://doi.org/10.1109/TETC.2023.3267909","url":null,"abstract":"The von Neumann architecture has been the status quo since the dawn of modern computing. Computers built on the von Neumann architecture are composed of an intelligent master processor (e.g., CPU) and dumb memory/storage devices incapable of computation (e.g., memory and disk). However, the skyrocketing data volume in modern computing is calling such status quo into question. The excessive amounts of data movement between processor and memory/storage in more and more real-world applications (e.g., machine learning and AI applications) have made the processor-centric design a severe power and performance bottleneck. The diminishing Moore's Law also raises the need for a memory-centric design, which is rising on top of the recent material advancement and manufacturing innovation to open a paradigm shift. By doing computation right inside or near the memory, the memory-centric design promises massive throughput and energy savings.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":null,"pages":null},"PeriodicalIF":5.9,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/6245516/10144811/10144915.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67883146","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}
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：