Vehicular edge computing (VEC), a promising paradigm for the development of emerging intelligent transportation systems, can provide lower service latency for vehicular applications. However, it is still a challenge to fulfill the requirements of such applications with stringent latency requirements in the VEC system with limited resources. In addition, existing methods focus on handling the offloading task in a certain time slot with statically allocated resources, but ignore the heterogeneous tasks' different resource requirements, resulting in resource wastage. To solve the real-time task offloading and heterogeneous resource allocation problem in VEC system, we propose a decentralized solution based on the attention mechanism and recurrent neural networks (RNN) with a multi-agent distributed deep deterministic policy gradient (AR-MAD4PG). First, to address the partial observability of agents, we construct a shared agent graph and propose a periodic communication mechanism that enables edge nodes to aggregate information from other edge nodes. Second, to help agents better understand the current system state, we design an RNN-based feature extraction network to capture the historical state and resource allocation information of the VEC system. Thirdly, to tackle the challenges of excessive joint observation-action space and ineffective information interference, we adopt the multi-head attention mechanism to compress the dimension of the observation-action space of agents. Finally, we build a simulation model based on the actual vehicle trajectories, and the experimental results show that our proposed method outperforms the existing approaches.
{"title":"Joint computation offloading and resource allocation for end-edge collaboration in internet of vehicles via multi-agent reinforcement learning.","authors":"Cong Wang, Yaoming Wang, Ying Yuan, Sancheng Peng, Guorui Li, Pengfei Yin","doi":"10.1016/j.neunet.2024.106621","DOIUrl":"10.1016/j.neunet.2024.106621","url":null,"abstract":"<p><p>Vehicular edge computing (VEC), a promising paradigm for the development of emerging intelligent transportation systems, can provide lower service latency for vehicular applications. However, it is still a challenge to fulfill the requirements of such applications with stringent latency requirements in the VEC system with limited resources. In addition, existing methods focus on handling the offloading task in a certain time slot with statically allocated resources, but ignore the heterogeneous tasks' different resource requirements, resulting in resource wastage. To solve the real-time task offloading and heterogeneous resource allocation problem in VEC system, we propose a decentralized solution based on the attention mechanism and recurrent neural networks (RNN) with a multi-agent distributed deep deterministic policy gradient (AR-MAD4PG). First, to address the partial observability of agents, we construct a shared agent graph and propose a periodic communication mechanism that enables edge nodes to aggregate information from other edge nodes. Second, to help agents better understand the current system state, we design an RNN-based feature extraction network to capture the historical state and resource allocation information of the VEC system. Thirdly, to tackle the challenges of excessive joint observation-action space and ineffective information interference, we adopt the multi-head attention mechanism to compress the dimension of the observation-action space of agents. Finally, we build a simulation model based on the actual vehicle trajectories, and the experimental results show that our proposed method outperforms the existing approaches.</p>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"179 ","pages":"106621"},"PeriodicalIF":6.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141996788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-11-01Epub Date: 2024-08-08DOI: 10.1016/j.neunet.2024.106603
Bo Li, Lingling Zhang, Jun Liu, Hong Peng, Qianying Wang, Jiaqi Liu
Multi-focus image fusion (MFIF) is an important technique that aims to combine the focused regions of multiple source images into a fully clear image. Decision-map methods are widely used in MFIF to maximize the preservation of information from the source images. While many decision-map methods have been proposed, they often struggle with difficulties in determining focus and non-focus boundaries, further affecting the quality of the fused images. Dynamic threshold neural P (DTNP) systems are computational models inspired by biological spiking neurons, featuring dynamic threshold and spiking mechanisms to better distinguish focused and unfocused regions for decision map generation. However, original DTNP systems require manual parameter configuration and have only one stimulus. Therefore, they are not suitable to be used directly for generating high-precision decision maps. To overcome these limitations, we propose a variant called parameter adaptive dual channel DTNP (PADCDTNP) systems. Inspired by the spiking mechanisms of PADCDTNP systems, we further develop a new MFIF method. As a new neural model, PADCDTNP systems adaptively estimate parameters according to multiple external inputs to produce decision maps with robust boundaries, resulting in high-quality fusion results. Comprehensive experiments on the Lytro/MFFW/MFI-WHU dataset show that our method achieves advanced performance and yields comparable results to the fourteen representative MFIF methods. In addition, compared to the standard DTNP systems, PADCDTNP systems improve the fusion performance and fusion efficiency on the three datasets by 5.69% and 86.03%, respectively. The codes for both the proposed method and the comparison methods are released at https://github.com/MorvanLi/MFIF-PADCDTNP.
{"title":"Multi-focus image fusion with parameter adaptive dual channel dynamic threshold neural P systems.","authors":"Bo Li, Lingling Zhang, Jun Liu, Hong Peng, Qianying Wang, Jiaqi Liu","doi":"10.1016/j.neunet.2024.106603","DOIUrl":"10.1016/j.neunet.2024.106603","url":null,"abstract":"<p><p>Multi-focus image fusion (MFIF) is an important technique that aims to combine the focused regions of multiple source images into a fully clear image. Decision-map methods are widely used in MFIF to maximize the preservation of information from the source images. While many decision-map methods have been proposed, they often struggle with difficulties in determining focus and non-focus boundaries, further affecting the quality of the fused images. Dynamic threshold neural P (DTNP) systems are computational models inspired by biological spiking neurons, featuring dynamic threshold and spiking mechanisms to better distinguish focused and unfocused regions for decision map generation. However, original DTNP systems require manual parameter configuration and have only one stimulus. Therefore, they are not suitable to be used directly for generating high-precision decision maps. To overcome these limitations, we propose a variant called parameter adaptive dual channel DTNP (PADCDTNP) systems. Inspired by the spiking mechanisms of PADCDTNP systems, we further develop a new MFIF method. As a new neural model, PADCDTNP systems adaptively estimate parameters according to multiple external inputs to produce decision maps with robust boundaries, resulting in high-quality fusion results. Comprehensive experiments on the Lytro/MFFW/MFI-WHU dataset show that our method achieves advanced performance and yields comparable results to the fourteen representative MFIF methods. In addition, compared to the standard DTNP systems, PADCDTNP systems improve the fusion performance and fusion efficiency on the three datasets by 5.69% and 86.03%, respectively. The codes for both the proposed method and the comparison methods are released at https://github.com/MorvanLi/MFIF-PADCDTNP.</p>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"179 ","pages":"106603"},"PeriodicalIF":6.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141989374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-11-01Epub Date: 2024-08-03DOI: 10.1016/j.neunet.2024.106590
Bilel Tarchoun, Anouar Ben Khalifa, Mohamed Ali Mahjoub, Nael Abu-Ghazaleh, Ihsen Alouani
Real-world adversarial patches were shown to be successful in compromising state-of-the-art models in various computer vision applications. Most existing defenses rely on analyzing input or feature level gradients to detect the patch. However, these methods have been compromised by recent GAN-based attacks that generate naturalistic patches. In this paper, we propose a new perspective to defend against adversarial patches based on the entropy carried by the input, rather than on its saliency. We present Jedi, a new defense against adversarial patches that tackles the patch localization problem from an information theory perspective; leveraging the high entropy of adversarial patches to identify potential patch zones, and using an autoencoder to complete patch regions from high entropy kernels. Jedi achieves high-precision adversarial patch localization and removal, detecting on average 90% of adversarial patches across different benchmarks, and recovering up to 94% of successful patch attacks. Since Jedi relies on an input entropy analysis, it is model-agnostic, and can be applied to off-the-shelf models without changes to the training or inference of the models. Moreover, we propose a comprehensive qualitative analysis that investigates the cases where Jedi fails, comparatively with related methods. Interestingly, we find a significant core failure cases among the different defenses share one common property: high entropy. We think that this work offers a new perspective to understand the adversarial effect under physical-world settings. We also leverage these findings to enhance Jedi's handling of entropy outliers by introducing Adaptive Jedi, which boosts performance by up to 9% in challenging images.
{"title":"An information-theoretic perspective of physical adversarial patches.","authors":"Bilel Tarchoun, Anouar Ben Khalifa, Mohamed Ali Mahjoub, Nael Abu-Ghazaleh, Ihsen Alouani","doi":"10.1016/j.neunet.2024.106590","DOIUrl":"10.1016/j.neunet.2024.106590","url":null,"abstract":"<p><p>Real-world adversarial patches were shown to be successful in compromising state-of-the-art models in various computer vision applications. Most existing defenses rely on analyzing input or feature level gradients to detect the patch. However, these methods have been compromised by recent GAN-based attacks that generate naturalistic patches. In this paper, we propose a new perspective to defend against adversarial patches based on the entropy carried by the input, rather than on its saliency. We present Jedi, a new defense against adversarial patches that tackles the patch localization problem from an information theory perspective; leveraging the high entropy of adversarial patches to identify potential patch zones, and using an autoencoder to complete patch regions from high entropy kernels. Jedi achieves high-precision adversarial patch localization and removal, detecting on average 90% of adversarial patches across different benchmarks, and recovering up to 94% of successful patch attacks. Since Jedi relies on an input entropy analysis, it is model-agnostic, and can be applied to off-the-shelf models without changes to the training or inference of the models. Moreover, we propose a comprehensive qualitative analysis that investigates the cases where Jedi fails, comparatively with related methods. Interestingly, we find a significant core failure cases among the different defenses share one common property: high entropy. We think that this work offers a new perspective to understand the adversarial effect under physical-world settings. We also leverage these findings to enhance Jedi's handling of entropy outliers by introducing Adaptive Jedi, which boosts performance by up to 9% in challenging images.</p>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"179 ","pages":"106590"},"PeriodicalIF":6.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142009846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-11-01DOI: 10.1016/j.neunet.2024.106842
Yalan Qin , Xinpeng Zhang , Shui Yu , Guorui Feng
Multi-view clustering has become a rapidly growing field in machine learning and data mining areas by combining useful information from different views for last decades. Although there have been some surveys based on multi-view clustering, most of these works ignore simultaneously taking the self-supervised and non-self supervised multi-view clustering into consideration. We give a novel survey for sorting out the existing algorithms of multi-view clustering in this work, which can be classified into two different categories, i.e., non-self supervised and self-supervised multi-view clustering. We first review the representative approaches based on the non-self supervised multi-view clustering, which consist of methods based on non-representation learning and representation learning. Furthermore, the methods built on non-representation learning contain works based on matrix factorization, kernel and other non-representation learning. Methods based on representation learning consist of multi-view graph clustering, deep representation learning and multi-view subspace clustering. For the methods based on self-supervised multi-view clustering, we divide them into contrastive methods and generative methods. Overall, this survey attempts to give an insightful overview regarding the developments in the multi-view clustering field.
{"title":"A survey on representation learning for multi-view data","authors":"Yalan Qin , Xinpeng Zhang , Shui Yu , Guorui Feng","doi":"10.1016/j.neunet.2024.106842","DOIUrl":"10.1016/j.neunet.2024.106842","url":null,"abstract":"<div><div>Multi-view clustering has become a rapidly growing field in machine learning and data mining areas by combining useful information from different views for last decades. Although there have been some surveys based on multi-view clustering, most of these works ignore simultaneously taking the self-supervised and non-self supervised multi-view clustering into consideration. We give a novel survey for sorting out the existing algorithms of multi-view clustering in this work, which can be classified into two different categories, i.e., non-self supervised and self-supervised multi-view clustering. We first review the representative approaches based on the non-self supervised multi-view clustering, which consist of methods based on non-representation learning and representation learning. Furthermore, the methods built on non-representation learning contain works based on matrix factorization, kernel and other non-representation learning. Methods based on representation learning consist of multi-view graph clustering, deep representation learning and multi-view subspace clustering. For the methods based on self-supervised multi-view clustering, we divide them into contrastive methods and generative methods. Overall, this survey attempts to give an insightful overview regarding the developments in the multi-view clustering field.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"Article 106842"},"PeriodicalIF":6.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142607177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-11-01DOI: 10.1016/j.neunet.2024.106850
Zihang Huang , Zhiwei Wang , Tianyu Zhao , Xiaohuan Ding , Xin Yang
Deep learning networks excel in image segmentation with abundant accurately annotated training samples. However, in medical applications, acquiring large quantities of high-quality labeled images is prohibitively expensive. Thus, learning from imperfect annotations (e.g. noisy or weak annotations) has emerged as a prominent research area in medical image segmentation. This work aims to extract high-quality pseudo masks from imperfect annotations with the assistance of a small number of clean labels. Our core motivation is based on the understanding that different types of flawed imperfect annotations inherently exhibit unique noise patterns. Comparing clean annotations with corresponding imperfectly annotated labels can effectively identify potential noise patterns at minimal additional cost. To this end, we propose a two-phase framework including a noise identification network and a noise-robust segmentation network. The former network implicitly learns noise patterns and revises labels accordingly. It includes a three-branch network to identify different types of noises. The latter one further mitigates the negative influence of residual annotation noises based on parallel segmentation networks with different initializations and a label softening strategy. Extensive experimental results on two public datasets demonstrate that our method can effectively refine annotation flaws and achieve superior segmentation performance to the state-of-the-art methods.
{"title":"Toward high-quality pseudo masks from noisy or weak annotations for robust medical image segmentation","authors":"Zihang Huang , Zhiwei Wang , Tianyu Zhao , Xiaohuan Ding , Xin Yang","doi":"10.1016/j.neunet.2024.106850","DOIUrl":"10.1016/j.neunet.2024.106850","url":null,"abstract":"<div><div>Deep learning networks excel in image segmentation with abundant accurately annotated training samples. However, in medical applications, acquiring large quantities of high-quality labeled images is prohibitively expensive. Thus, learning from imperfect annotations (e.g. noisy or weak annotations) has emerged as a prominent research area in medical image segmentation. This work aims to extract high-quality pseudo masks from imperfect annotations with the assistance of a small number of clean labels. Our core motivation is based on the understanding that different types of flawed imperfect annotations inherently exhibit unique noise patterns. Comparing clean annotations with corresponding imperfectly annotated labels can effectively identify potential noise patterns at minimal additional cost. To this end, we propose a two-phase framework including a noise identification network and a noise-robust segmentation network. The former network implicitly learns noise patterns and revises labels accordingly. It includes a three-branch network to identify different types of noises. The latter one further mitigates the negative influence of residual annotation noises based on parallel segmentation networks with different initializations and a label softening strategy. Extensive experimental results on two public datasets demonstrate that our method can effectively refine annotation flaws and achieve superior segmentation performance to the state-of-the-art methods.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"Article 106850"},"PeriodicalIF":6.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142631418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-11-01DOI: 10.1016/j.neunet.2024.106848
Jinfeng Li, Biao Luo, Xiaodong Xu, Tingwen Huang
Designing reward functions that fully align with human intent is often challenging. Preference-based Reinforcement Learning (PbRL) provides a framework where humans can select preferred segments through pairwise comparisons of behavior trajectory segments, facilitating reward function learning. However, existing methods collect non-dynamic preferences and struggle to provide accurate information about preference intensity. We propose scaling preference (SP) feedback method and qualitative and quantitative scaling preference (Q2SP) feedback method, which allow humans to express the true degree of preference between trajectories, thus helping reward learn more accurate human preferences from offline data. Our key insight is that more detailed feedback facilitates the learning of reward functions that better align with human intent. Experiments demonstrate that, across a range of control and robotic benchmark tasks, our methods are highly competitive compared to baselines and state of the art approaches.
{"title":"Offline reward shaping with scaling human preference feedback for deep reinforcement learning","authors":"Jinfeng Li, Biao Luo, Xiaodong Xu, Tingwen Huang","doi":"10.1016/j.neunet.2024.106848","DOIUrl":"10.1016/j.neunet.2024.106848","url":null,"abstract":"<div><div>Designing reward functions that fully align with human intent is often challenging. Preference-based Reinforcement Learning (PbRL) provides a framework where humans can select preferred segments through pairwise comparisons of behavior trajectory segments, facilitating reward function learning. However, existing methods collect non-dynamic preferences and struggle to provide accurate information about preference intensity. We propose scaling preference (SP) feedback method and qualitative and quantitative scaling preference (Q2SP) feedback method, which allow humans to express the true degree of preference between trajectories, thus helping reward learn more accurate human preferences from offline data. Our key insight is that more detailed feedback facilitates the learning of reward functions that better align with human intent. Experiments demonstrate that, across a range of control and robotic benchmark tasks, our methods are highly competitive compared to baselines and state of the art approaches.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"Article 106848"},"PeriodicalIF":6.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142607193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-11-01DOI: 10.1016/j.neunet.2024.106844
Xujin Li , Wei Wei , Shuang Qiu , Huiguang He
The Rapid Serial Visual Presentation (RSVP)-based Brain–Computer Interface (BCI) is an efficient technology for target retrieval using electroencephalography (EEG) signals. The performance improvement of traditional decoding methods relies on a substantial amount of training data from new test subjects, which increases preparation time for BCI systems. Several studies introduce data from existing subjects to reduce the dependence of performance improvement on data from new subjects, but their optimization strategy based on adversarial learning with extensive data increases training time during the preparation procedure. Moreover, most previous methods only focus on the single-view information of EEG signals, but ignore the information from other views which may further improve performance. To enhance decoding performance while reducing preparation time, we propose a Temporal-Spectral fusion transformer with Subject-specific Adapter (TSformer-SA). Specifically, a cross-view interaction module is proposed to facilitate information transfer and extract common representations across two-view features extracted from EEG temporal signals and spectrogram images. Then, an attention-based fusion module fuses the features of two views to obtain comprehensive discriminative features for classification. Furthermore, a multi-view consistency loss is proposed to maximize the feature similarity between two views of the same EEG signal. Finally, we propose a subject-specific adapter to rapidly transfer the knowledge of the model trained on data from existing subjects to decode data from new subjects. Experimental results show that TSformer-SA significantly outperforms comparison methods and achieves outstanding performance with limited training data from new subjects. This facilitates efficient decoding and rapid deployment of BCI systems in practical use.
{"title":"A temporal–spectral fusion transformer with subject-specific adapter for enhancing RSVP-BCI decoding","authors":"Xujin Li , Wei Wei , Shuang Qiu , Huiguang He","doi":"10.1016/j.neunet.2024.106844","DOIUrl":"10.1016/j.neunet.2024.106844","url":null,"abstract":"<div><div>The Rapid Serial Visual Presentation (RSVP)-based Brain–Computer Interface (BCI) is an efficient technology for target retrieval using electroencephalography (EEG) signals. The performance improvement of traditional decoding methods relies on a substantial amount of training data from new test subjects, which increases preparation time for BCI systems. Several studies introduce data from existing subjects to reduce the dependence of performance improvement on data from new subjects, but their optimization strategy based on adversarial learning with extensive data increases training time during the preparation procedure. Moreover, most previous methods only focus on the single-view information of EEG signals, but ignore the information from other views which may further improve performance. To enhance decoding performance while reducing preparation time, we propose a <strong>T</strong>emporal-<strong>S</strong>pectral fusion trans<strong>former</strong> with <strong>S</strong>ubject-specific <strong>A</strong>dapter (TSformer-SA). Specifically, a cross-view interaction module is proposed to facilitate information transfer and extract common representations across two-view features extracted from EEG temporal signals and spectrogram images. Then, an attention-based fusion module fuses the features of two views to obtain comprehensive discriminative features for classification. Furthermore, a multi-view consistency loss is proposed to maximize the feature similarity between two views of the same EEG signal. Finally, we propose a subject-specific adapter to rapidly transfer the knowledge of the model trained on data from existing subjects to decode data from new subjects. Experimental results show that TSformer-SA significantly outperforms comparison methods and achieves outstanding performance with limited training data from new subjects. This facilitates efficient decoding and rapid deployment of BCI systems in practical use.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"Article 106844"},"PeriodicalIF":6.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142607179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-10-31DOI: 10.1016/j.neunet.2024.106846
Yunhui Liu, Tieke He, Tao Zheng, Jianhua Zhao
Graph Contrastive Learning (GCL) has recently emerged as a promising graph self-supervised learning framework for learning discriminative node representations without labels. The widely adopted objective function of GCL benefits from two key properties: alignment and uniformity, which align representations of positive node pairs while uniformly distributing all representations on the hypersphere. The uniformity property plays a critical role in preventing representation collapse and is achieved by pushing apart augmented views of different nodes (negative pairs). As such, existing GCL methods inherently rely on increasing the quantity and quality of negative samples, resulting in heavy computational demands, memory overhead, and potential class collision issues. In this study, we propose a negative-free objective to achieve uniformity, inspired by the fact that points distributed according to a normalized isotropic Gaussian are uniformly spread across the unit hypersphere. Therefore, we can minimize the distance between the distribution of learned representations and the isotropic Gaussian distribution to promote the uniformity of node representations. Our method also distinguishes itself from other approaches by eliminating the need for a parameterized mutual information estimator, an additional projector, asymmetric structures, and, crucially, negative samples. Extensive experiments over seven graph benchmarks demonstrate that our proposal achieves competitive performance with fewer parameters, shorter training times, and lower memory consumption compared to existing GCL methods.
{"title":"Negative-Free Self-Supervised Gaussian Embedding of Graphs","authors":"Yunhui Liu, Tieke He, Tao Zheng, Jianhua Zhao","doi":"10.1016/j.neunet.2024.106846","DOIUrl":"10.1016/j.neunet.2024.106846","url":null,"abstract":"<div><div>Graph Contrastive Learning (GCL) has recently emerged as a promising graph self-supervised learning framework for learning discriminative node representations without labels. The widely adopted objective function of GCL benefits from two key properties: <em>alignment</em> and <em>uniformity</em>, which align representations of positive node pairs while uniformly distributing all representations on the hypersphere. The uniformity property plays a critical role in preventing representation collapse and is achieved by pushing apart augmented views of different nodes (negative pairs). As such, existing GCL methods inherently rely on increasing the quantity and quality of negative samples, resulting in heavy computational demands, memory overhead, and potential class collision issues. In this study, we propose a negative-free objective to achieve uniformity, inspired by the fact that points distributed according to a normalized isotropic Gaussian are uniformly spread across the unit hypersphere. Therefore, we can minimize the distance between the distribution of learned representations and the isotropic Gaussian distribution to promote the uniformity of node representations. Our method also distinguishes itself from other approaches by eliminating the need for a parameterized mutual information estimator, an additional projector, asymmetric structures, and, crucially, negative samples. Extensive experiments over seven graph benchmarks demonstrate that our proposal achieves competitive performance with fewer parameters, shorter training times, and lower memory consumption compared to existing GCL methods.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"Article 106846"},"PeriodicalIF":6.0,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142607191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Feature selection (FS) is essential in machine learning and data mining as it makes handling high-dimensional data more efficient and reliable. More attention has been paid to unsupervised feature selection (UFS) due to the extra resources required to obtain labels for data in the real world. Most of the existing embedded UFS utilize a sparse projection matrix for FS. However, this may introduce additional regularization terms, and it is difficult to control the sparsity of the projection matrix well. Moreover, such methods may seriously destroy the original feature structure in the embedding space. Instead, avoiding projecting the original data into the low-dimensional embedding space and identifying features directly from the raw features that perform well in the process of making the data show a distinct cluster structure is a feasible solution. Inspired by this, this paper proposes a model called A General Adaptive Unsupervised Feature Selection with Auto-weighting (GAWFS), which utilizes two techniques, non-negative matrix factorization, and adaptive graph learning, to simulate the process of dividing data into clusters, and identifies the features that are most discriminative in the clustering process by a feature weighting matrix . Since the weighting matrix is sparse, it also plays the role of FS or a filter. Finally, experiments comparing GAWFS with several state-of-the-art UFS methods on synthetic datasets and real-world datasets are conducted, and the results demonstrate the superiority of the GAWFS.
{"title":"A general adaptive unsupervised feature selection with auto-weighting","authors":"Huming Liao , Hongmei Chen , Tengyu Yin , Zhong Yuan , Shi-Jinn Horng , Tianrui Li","doi":"10.1016/j.neunet.2024.106840","DOIUrl":"10.1016/j.neunet.2024.106840","url":null,"abstract":"<div><div>Feature selection (FS) is essential in machine learning and data mining as it makes handling high-dimensional data more efficient and reliable. More attention has been paid to unsupervised feature selection (UFS) due to the extra resources required to obtain labels for data in the real world. Most of the existing embedded UFS utilize a sparse projection matrix for FS. However, this may introduce additional regularization terms, and it is difficult to control the sparsity of the projection matrix well. Moreover, such methods may seriously destroy the original feature structure in the embedding space. Instead, avoiding projecting the original data into the low-dimensional embedding space and identifying features directly from the raw features that perform well in the process of making the data show a distinct cluster structure is a feasible solution. Inspired by this, this paper proposes a model called A General Adaptive Unsupervised Feature Selection with Auto-weighting (GAWFS), which utilizes two techniques, non-negative matrix factorization, and adaptive graph learning, to simulate the process of dividing data into clusters, and identifies the features that are most discriminative in the clustering process by a feature weighting matrix <span><math><mi>Θ</mi></math></span>. Since the weighting matrix is sparse, it also plays the role of FS or a filter. Finally, experiments comparing GAWFS with several state-of-the-art UFS methods on synthetic datasets and real-world datasets are conducted, and the results demonstrate the superiority of the GAWFS.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"Article 106840"},"PeriodicalIF":6.0,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142607175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-10-31DOI: 10.1016/j.neunet.2024.106843
Fenglan Sun , Xuemei Yu , Wei Zhu , Jürgen Kurths
The time-varying formation problem of singular multi-agent systems under sampled data with multiple leaders is investigated in this paper. Firstly, a data-sampled time-varying formation control protocol is proposed in the current study where the communication among followers merely occurred at sampling instants, which can save the controller communication energy significantly. Secondly, necessary and sufficient conditions for the feasibility of the formation function are provided. In addition, an approach is presented to design the formation tracking control under sampled data with multiple leaders. Finally, numerical simulations validate the efficacy of the theoretical results.
{"title":"Data-sampled time-varying formation for singular multi-agent systems with multiple leaders","authors":"Fenglan Sun , Xuemei Yu , Wei Zhu , Jürgen Kurths","doi":"10.1016/j.neunet.2024.106843","DOIUrl":"10.1016/j.neunet.2024.106843","url":null,"abstract":"<div><div>The time-varying formation problem of singular multi-agent systems under sampled data with multiple leaders is investigated in this paper. Firstly, a data-sampled time-varying formation control protocol is proposed in the current study where the communication among followers merely occurred at sampling instants, which can save the controller communication energy significantly. Secondly, necessary and sufficient conditions for the feasibility of the formation function are provided. In addition, an approach is presented to design the formation tracking control under sampled data with multiple leaders. Finally, numerical simulations validate the efficacy of the theoretical results.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"Article 106843"},"PeriodicalIF":6.0,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142607183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}