Research

14 pages, 595 KiB

Open AccessArticle

Enhancing Zero-Shot Stance Detection with Contrastive and Prompt Learning

by Zhenyin Yao, Wenzhong Yang and Fuyuan Wei

Entropy 2024, 26(4), 325; https://doi.org/10.3390/e26040325 - 11 Apr 2024

Viewed by 309

In social networks, the occurrence of unexpected events rapidly catalyzes the widespread dissemination and further evolution of network public opinion. The advent of zero-shot stance detection aligns more closely with the characteristics of stance detection in today’s digital age, where the absence of [...] Read more.

In social networks, the occurrence of unexpected events rapidly catalyzes the widespread dissemination and further evolution of network public opinion. The advent of zero-shot stance detection aligns more closely with the characteristics of stance detection in today’s digital age, where the absence of training examples for specific models poses significant challenges. This task necessitates models with robust generalization abilities to discern target-related, transferable stance features within training data. Recent advances in prompt-based learning have showcased notable efficacy in few-shot text classification. Such methods typically employ a uniform prompt pattern across all instances, yet they overlook the intricate relationship between prompts and instances, thereby failing to sufficiently direct the model towards learning task-relevant knowledge and information. This paper argues for the critical need to dynamically enhance the relevance between specific instances and prompts. Thus, we introduce a stance detection model underpinned by a gated multilayer perceptron (gMLP) and a prompt learning strategy, which is tailored for zero-shot stance detection scenarios. Specifically, the gMLP is utilized to capture semantic features of instances, coupled with a control gate mechanism to modulate the influence of the gate on prompt tokens based on the semantic context of each instance, thereby dynamically reinforcing the instance–prompt connection. Moreover, we integrate contrastive learning to empower the model with more discriminative feature representations. Experimental evaluations on the VAST and SEM16 benchmark datasets substantiate our method’s effectiveness, yielding a 1.3% improvement over the JointCL model on the VAST dataset. Full article

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing II)

► Show Figures

Figure 1

22 pages, 4753 KiB

Open AccessArticle

An N-Shaped Lightweight Network with a Feature Pyramid and Hybrid Attention for Brain Tumor Segmentation

by Mengxian Chi, Hong An, Xu Jin and Zhenguo Nie

Entropy 2024, 26(2), 166; https://doi.org/10.3390/e26020166 - 15 Feb 2024

Viewed by 828

Abstract

Brain tumor segmentation using neural networks presents challenges in accurately capturing diverse tumor shapes and sizes while maintaining real-time performance. Additionally, addressing class imbalance is crucial for achieving accurate clinical results. To tackle these issues, this study proposes a novel N-shaped lightweight network [...] Read more.

Brain tumor segmentation using neural networks presents challenges in accurately capturing diverse tumor shapes and sizes while maintaining real-time performance. Additionally, addressing class imbalance is crucial for achieving accurate clinical results. To tackle these issues, this study proposes a novel N-shaped lightweight network that combines multiple feature pyramid paths and U-Net architectures. Furthermore, we ingeniously integrate hybrid attention mechanisms into various locations of depth-wise separable convolution module to improve efficiency, with channel attention found to be the most effective for skip connections in the proposed network. Moreover, we introduce a combination loss function that incorporates a newly designed weighted cross-entropy loss and dice loss to effectively tackle the issue of class imbalance. Extensive experiments are conducted on four publicly available datasets, i.e., UCSF-PDGM, BraTS 2021, BraTS 2019, and MSD Task 01 to evaluate the performance of different methods. The results demonstrate that the proposed network achieves superior segmentation accuracy compared to state-of-the-art methods. The proposed network not only improves the overall segmentation performance but also provides a favorable computational efficiency, making it a promising approach for clinical applications. Full article

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing II)

► Show Figures

Figure 1

21 pages, 1422 KiB

Open AccessArticle

Lightweight Cross-Modal Information Mutual Reinforcement Network for RGB-T Salient Object Detection

by Chengtao Lv, Bin Wan, Xiaofei Zhou, Yaoqi Sun, Jiyong Zhang and Chenggang Yan

Entropy 2024, 26(2), 130; https://doi.org/10.3390/e26020130 - 31 Jan 2024

Viewed by 674

Abstract

RGB-T salient object detection (SOD) has made significant progress in recent years. However, most existing works are based on heavy models, which are not applicable to mobile devices. Additionally, there is still room for improvement in the design of cross-modal feature fusion and [...] Read more.

RGB-T salient object detection (SOD) has made significant progress in recent years. However, most existing works are based on heavy models, which are not applicable to mobile devices. Additionally, there is still room for improvement in the design of cross-modal feature fusion and cross-level feature fusion. To address these issues, we propose a lightweight cross-modal information mutual reinforcement network for RGB-T SOD. Our network consists of a lightweight encoder, the cross-modal information mutual reinforcement (CMIMR) module, and the semantic-information-guided fusion (SIGF) module. To reduce the computational cost and the number of parameters, we employ the lightweight module in both the encoder and decoder. Furthermore, to fuse the complementary information between two-modal features, we design the CMIMR module to enhance the two-modal features. This module effectively refines the two-modal features by absorbing previous-level semantic information and inter-modal complementary information. In addition, to fuse the cross-level feature and detect multiscale salient objects, we design the SIGF module, which effectively suppresses the background noisy information in low-level features and extracts multiscale information. We conduct extensive experiments on three RGB-T datasets, and our method achieves competitive performance compared to the other 15 state-of-the-art methods. Full article

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing II)

► Show Figures

Figure 1

14 pages, 551 KiB

Open AccessArticle

FLPP: A Federated-Learning-Based Scheme for Privacy Protection in Mobile Edge Computing

by Zhimo Cheng, Xinsheng Ji, Wei You, Yi Bai, Yunjie Chen and Xiaogang Qin

Entropy 2023, 25(11), 1551; https://doi.org/10.3390/e25111551 - 16 Nov 2023

Viewed by 909

Abstract

Data sharing and analyzing among different devices in mobile edge computing is valuable for social innovation and development. The limitation to the achievement of this goal is the data privacy risk. Therefore, existing studies mainly focus on enhancing the data privacy-protection capability. On [...] Read more.

Data sharing and analyzing among different devices in mobile edge computing is valuable for social innovation and development. The limitation to the achievement of this goal is the data privacy risk. Therefore, existing studies mainly focus on enhancing the data privacy-protection capability. On the one hand, direct data leakage is avoided through federated learning by converting raw data into model parameters for transmission. On the other hand, the security of federated learning is further strengthened by privacy-protection techniques to defend against inference attack. However, privacy-protection techniques may reduce the training accuracy of the data while improving the security. Particularly, trading off data security and accuracy is a major challenge in dynamic mobile edge computing scenarios. To address this issue, we propose a federated-learning-based privacy-protection scheme, FLPP. Then, we build a layered adaptive differential privacy model to dynamically adjust the privacy-protection level in different situations. Finally, we design a differential evolutionary algorithm to derive the most suitable privacy-protection policy for achieving the optimal overall performance. The simulation results show that FLPP has an advantage of 8∼34% in overall performance. This demonstrates that our scheme can enable data to be shared securely and accurately. Full article

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing II)

► Show Figures

Figure 1

12 pages, 678 KiB

Open AccessArticle

Degree-Aware Graph Neural Network Quantization

by Ziqin Fan and Xi Jin

Entropy 2023, 25(11), 1510; https://doi.org/10.3390/e25111510 - 02 Nov 2023

Viewed by 875

Abstract

In this paper, we investigate the problem of graph neural network quantization. Despite the great success on convolutional neural networks, directly applying current network quantization approaches to graph neural networks faces two challenges. First, the fixed-scale parameter in the current methods cannot flexibly [...] Read more.

In this paper, we investigate the problem of graph neural network quantization. Despite the great success on convolutional neural networks, directly applying current network quantization approaches to graph neural networks faces two challenges. First, the fixed-scale parameter in the current methods cannot flexibly fit diverse tasks and network architectures. Second, the variations of node degree in a graph leads to uneven responses, limiting the accuracy of the quantizer. To address these two challenges, we introduce learnable scale parameters that can be optimized jointly with the graph networks. In addition, we propose degree-aware normalization to process nodes with different degrees. Experiments on different tasks, baselines, and datasets demonstrate the superiority of our method against previous state-of-the-art ones. Full article

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing II)

► Show Figures

Figure 1

16 pages, 1390 KiB

Open AccessArticle

Convolutional Models with Multi-Feature Fusion for Effective Link Prediction in Knowledge Graph Embedding

by Qinglang Guo, Yong Liao, Zhe Li, Hui Lin and Shenglin Liang

Entropy 2023, 25(10), 1472; https://doi.org/10.3390/e25101472 - 21 Oct 2023

Viewed by 934

Abstract

Link prediction remains paramount in knowledge graph embedding (KGE), aiming to discern obscured or non-manifest relationships within a given knowledge graph (KG). Despite the critical nature of this endeavor, contemporary methodologies grapple with notable constraints, predominantly in terms of computational overhead and the [...] Read more.

Link prediction remains paramount in knowledge graph embedding (KGE), aiming to discern obscured or non-manifest relationships within a given knowledge graph (KG). Despite the critical nature of this endeavor, contemporary methodologies grapple with notable constraints, predominantly in terms of computational overhead and the intricacy of encapsulating multifaceted relationships. This paper introduces a sophisticated approach that amalgamates convolutional operators with pertinent graph structural information. By meticulously integrating information pertinent to entities and their immediate relational neighbors, we enhance the performance of the convolutional model, culminating in an averaged embedding ensuing from the convolution across entities and their proximal nodes. Significantly, our methodology presents a distinctive avenue, facilitating the inclusion of edge-specific data into the convolutional model’s input, thus endowing users with the latitude to calibrate the model’s architecture and parameters congruent with their specific dataset. Empirical evaluations underscore the ascendancy of our proposition over extant convolution-based link prediction benchmarks, particularly evident across the FB15k, WN18, and YAGO3-10 datasets. The primary objective of this research lies in forging KGE link prediction methodologies imbued with heightened efficiency and adeptness, thereby addressing salient challenges inherent to real-world applications. Full article

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing II)

► Show Figures

Figure 1

19 pages, 8211 KiB

Open AccessArticle

Multi-Focus Image Fusion for Full-Field Optical Angiography

by Yuchan Jie, Xiaosong Li, Mingyi Wang and Haishu Tan

Entropy 2023, 25(6), 951; https://doi.org/10.3390/e25060951 - 16 Jun 2023

Cited by 1 | Viewed by 1070

Abstract

Full-field optical angiography (FFOA) has considerable potential for clinical applications in the prevention and diagnosis of various diseases. However, owing to the limited depth of focus attainable using optical lenses, only information about blood flow in the plane within the depth of field [...] Read more.

Full-field optical angiography (FFOA) has considerable potential for clinical applications in the prevention and diagnosis of various diseases. However, owing to the limited depth of focus attainable using optical lenses, only information about blood flow in the plane within the depth of field can be acquired using existing FFOA imaging techniques, resulting in partially unclear images. To produce fully focused FFOA images, an FFOA image fusion method based on the nonsubsampled contourlet transform and contrast spatial frequency is proposed. Firstly, an imaging system is constructed, and the FFOA images are acquired by intensity-fluctuation modulation effect. Secondly, we decompose the source images into low-pass and bandpass images by performing nonsubsampled contourlet transform. A sparse representation-based rule is introduced to fuse the lowpass images to effectively retain the useful energy information. Meanwhile, a contrast spatial frequency rule is proposed to fuse bandpass images, which considers the neighborhood correlation and gradient relationships of pixels. Finally, the fully focused image is produced by reconstruction. The proposed method significantly expands the range of focus of optical angiography and can be effectively extended to public multi-focused datasets. Experimental results confirm that the proposed method outperformed some state-of-the-art methods in both qualitative and quantitative evaluations. Full article

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing II)

► Show Figures

Figure 1

21 pages, 505 KiB

Open AccessArticle

IMF: Interpretable Multi-Hop Forecasting on Temporal Knowledge Graphs

by Zhenyu Du, Lingzhi Qu, Zongwei Liang, Keju Huang, Lin Cui and Zhiyang Gao

Entropy 2023, 25(4), 666; https://doi.org/10.3390/e25040666 - 16 Apr 2023

Cited by 1 | Viewed by 1841

Abstract

Temporal knowledge graphs (KGs) have recently attracted increasing attention. The temporal KG forecasting task, which plays a crucial role in such applications as event prediction, predicts future links based on historical facts. However, current studies pay scant attention to the following two aspects. [...] Read more.

Temporal knowledge graphs (KGs) have recently attracted increasing attention. The temporal KG forecasting task, which plays a crucial role in such applications as event prediction, predicts future links based on historical facts. However, current studies pay scant attention to the following two aspects. First, the interpretability of current models is manifested in providing reasoning paths, which is an essential property of path-based models. However, the comparison of reasoning paths in these models is operated in a black-box fashion. Moreover, contemporary models utilize separate networks to evaluate paths at different hops. Although the network for each hop has the same architecture, each network achieves different parameters for better performance. Different parameters cause identical semantics to have different scores, so models cannot measure identical semantics at different hops equally. Inspired by the observation that reasoning based on multi-hop paths is akin to answering questions step by step, this paper designs an Interpretable Multi-Hop Reasoning (IMR) framework based on consistent basic models for temporal KG forecasting. IMR transforms reasoning based on path searching into stepwise question answering. In addition, IMR develops three indicators according to the characteristics of temporal KGs and reasoning paths: the question matching degree, answer completion level, and path confidence. IMR can uniformly integrate paths of different hops according to the same criteria; IMR can provide the reasoning paths similarly to other interpretable models and further explain the basis for path comparison. We instantiate the framework based on common embedding models such as TransE, RotatE, and ComplEx. While being more explainable, these instantiated models achieve state-of-the-art performance against previous models on four baseline datasets. Full article

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing II)

► Show Figures