Breast ultrasound tumor segmentation is critical for early diagnosis and treatment planning. However, due to the high similarity between tumors and background tissue in ultrasound images, achieving accurate segmentation poses significant challenges. To address this, we propose a Masked Separable Attention Network (MSA-Net), a segmentation model based on an encoder-decoder architecture. The model employs PVTv2 as the feature extraction backbone encoder and introduces our designed Masked Separable Attention (MSA) module. The core innovation of the MSA module lies in separating the multi-head self-attention mechanism into three function-specific subgroups: the foreground attention group focuses on the tumor region, the background attention group focuses on the surrounding tissue, and the global attention group captures the overall image information. This structured attention mechanism aims to more effectively model the contextual relationships between the tumor region, background region, and the entire image, thereby significantly enhancing the model's ability to distinguish between tumors and background tissue. Extensive experiments demonstrate that our MSA-Net achieves competitive performance compared to state-of-the-art breast tumor segmentation methods. Ablation studies further confirm the effectiveness and complementary of each component in our MSA-Net. The code is available at https://github.com/chenwang1701/MSA-Net.

As a building block of knowledge acquisition, knowledge graph completion (KGC) aims at inferring missing facts in knowledge graphs (KGs) automatically. Previous studies mainly focus on graph convolutional network (GCN)-based KG embedding (KGE) to determine the representations of entities and relations, accordingly predicting missing triplets. However, most existing KGE methods suffer from limitations in predicting tail entities that are far away or even unreachable in KGs. This limitation can be attributed to the related high-order information being largely ignored. In this work, we focus on learning the information from the related high-order neighbors in KGs to improve the performance of prediction. Specifically, we first introduce a set of new nodes called pedalnodes to augment the KGs for facilitating message passing between related high-order entities, effectively injecting the information of high-order neighbors into entity representation. Additionally, we propose strength-guided graph neural networks to aggregate neighboring entity representations. To address the issue of transmitting irrelevant higher order information to entities through pedal nodes, which can potentially hurt entity representation, we further propose to dynamically integrate the aggregated representation of each node with its corresponding self-representation. Extensive experiments have been conducted on three benchmark datasets and the results demonstrate the superiority of our method compared to strong baseline models.

Graph neural networks (GNNs) have significantly advanced our ability to mine structured data, playing a central role in areas such as social networks and recommendation systems. However, while most GNN-based methods focus on learning node representations in static graphs, they often ignore the dynamic nature of real-world networks, limiting their applicability. Furthermore, existing dynamic representation learning methods using Hawkes point processes, while capable of modeling event sequences, are inherently transductive and tailored to specific scenarios with dual timescales and mixed event types, thus not fully generalizable. To bridge this gap, we introduce DNRHP, a novel framework for learning temporal network representations. Specifically, DNRHP integrates historical edge (HE) information with the network's evolutionary properties, using the Hawkes point process to model edge formation. It captures not only the influence of past events on the likelihood of future connections but also the impact of the structural evolution of the network. The novelty of our model lies in its comprehensive consideration of the dynamics of network evolution and historical connectivity, allowing for a more accurate representation of nodes and their interactions over time. Extensive experiments on diverse real-world networks demonstrate the effectiveness of DNRHP, outperforming state-of-the-art baselines in terms of accuracy and efficiency for tasks such as node classification and link prediction.

In the field of biomedicine, Document-level relation extraction (DocRE) aims to reason about complex relational facts among entities by reading, inferring, and aggregating among entities over multiple sentences in a document. Existing studies construct document-level graphs to enrich interactions between entities. However, these methods pay more attention to the entity nodes and their connections, regardless of the rich knowledge entailed in the original corpus. In this paper, we propose a contrastive learning enhanced document-level graph relation representation(CGDRE) which mines the semantic knowledge from the original corpus and improve the ability of DocRE. Firstly, we use a coreference contrastive learning module to capture the potential semantic knowledge. Secondly, we construct a heterogeneous graph to enhance the graph structure information according to the original document and semantic knowledge. Lastly, CGDRE infers relations on the aggregated graph and uses focal loss to train the model. Remarkably, it is amazing that CGDRE can effectively alleviate the long-tailed distribution problem in the DocRE. Experiments on the public datasets, CDR, GDA and DocRED, show that CGDRE can significantly outperform other baselines, achieving a significant performance improvement. Extensive analyses demonstrate that the performance of our CGDRE is contributed by the capture of the semantic knowledge enhanced graph relation representation.

Document-level relation extraction is an important task in natural language processing that involves identifying and classifying relations between entities mentioned in a document. Traditional approaches often focus on individual sentences or local context, overlooking the broader context of the entire document. In this paper, we propose an Evidence Sentence Augmented Sequence-to-Sequence method for Document-level Relation Extraction(called ESASS-DRE). Our method introduces evidence sentences into the sequence-to-sequence framework to improve document-level relation extraction. The approach consists of two main steps: evidence sentence selection and relation extraction. Firstly, we identify a set of evidence sentences that contain crucial information relevant to the target relation. These sentences are selected based on their importance and contextual relevance. Secondly, the selected evidence sentences are combined with the original document and used as input to the sequence-to-sequence model. These generated sequences are decoded into relation labels, indicating the type of relationship between the entities. By incorporating evidence sentences into the model, we provide additional context and relevant information, enabling the model to make more informed predictions. Experiments conducted on benchmark datasets demonstrate the effectiveness of our method. Compared to traditional approaches, our method achieves higher accuracy and robustness in document-level relation extraction tasks. The incorporation of evidence sentences allows the model to capture the broader context of the document, leading to improved performance. (e.g., by 2.96/3.64 Ign F1/F1 on DocRED).

Efficient semantic segmentation is essential for a wide array of computer vision applications, and knowledge distillation has emerged as a promising methodology for model compression and efficiency. However, we observed that an excess of positive pixels can dilute attention weights, hindering the student model’s learning process. To tackle this significant challenge, we introduce the Local and Global Attention Distillation (LGAD) framework, a pioneering block-based technique that distills both local and global attention. The LGAD framework segments feature maps and output probabilities into well-defined local and global blocks, effectively mitigating the dilution of attention weights. By doing so, it enhances the distinction between positive and negative pixels, particularly amplifying the focus on salient regions within each local and global block. We have conducted comprehensive experiments on three benchmark datasets, Cityscapes, CamVid, and Pascal VOC 2012. The experiment results demonstrate the effectiveness of our proposed LGAD and confirm its superiority over several state-of-the-art distillation methods for semantic segmentation.

Knowledge graph completion (KGC) aims at inferring missing links between two entities. Most previous models focus on learning representations for entities and relations via graph neural networks. In this formalism, representations heavily rely on structural information. However, it is common for Knowledge graphs (KGs) to be unconnected due to their inherent incompleteness, resulting in a significant loss of vital structural information. To overcome this issue, this paper proposes to increase the connectedness of KGs to facilitate message passing between entities. Specifically, we first augment KGs with a series of auxiliary triplets derived from outer nodes. Subsequently, a dynamically weighted graph convolutional layer is employed to unequally aggregate the representations of neighboring entities and dynamically combine this aggregated information with information from themselves. Finally, ConvE is utilized to calculate scores for all triplets. Extensive experiments on two benchmark datasets demonstrate the superiority of our method compared to strong baseline models.

Relation extraction is one of the most essential tasks of knowledge construction, but it depends on a large amount of annotated data corpus. Few-shot relation extraction is proposed as a new paradigm, which is designed to learn new relationships between entities with merely a small number of annotated instances, effectively mitigating the cost of large-scale annotation and long-tail problems. To generalize to novel classes not included in the training set, existing approaches mainly focus on tuning pre-trained language models with relation instructions and developing class prototypes based on metric learning to extract relations. However, the learned representations are extremely sensitive to discrepancies in intra-class and inter-class relationships and hard to adaptively classify the relations due to biased class features and spurious correlations, such as similar relation classes having closer inter-class prototype representation. In this paper, we introduce an adaptive class augmented prototype network with instance-level and representation-level augmented mechanisms to strengthen the representation space. Specifically, we design the adaptive class augmentation mechanism to expand the representation of classes in instance-level augmentation, and class augmented representation learning with Bernoulli perturbation context attention to enhance the representation of class features in representation-level augmentation and explore adaptive debiased contrastive learning to train the model. Experimental results have been demonstrated on FewRel and NYT-25 under various few-shot settings, and the proposed model has improved accuracy and generalization, especially for cross-domain and different hard tasks.

Crack segmentation is a critical component in structural health monitoring. Conventional crack segmentation models usually focus on optimizing the cross-entropy-based objective function and overlook the optimization of the subsequent binarization process. In this paper, we redefine the crack segmentation problem as a joint optimization problem, which requires optimizing the binarization process in addition to the objective function of the segmentation model. Simultaneously optimizing both processes demonstrates significant improvements in the model’s segmentation performance. To optimize the binarization process, we propose the Adaptive Dynamic Thresholding Module (ADTM), which reuses the spatial features in the segmentation network to perform an additional regression task to obtain the optimal threshold for each crack image. ADTM is a pluggable component for practical deployment, consuming only a small amount of additional memory during deployment while significantly improving inference accuracy. Experimental results using four different datasets with diverse sources and distributions for crack semantic and instance segmentation demonstrate the effectiveness of ADTM in improving segmentation performance. While ADTM has only been evaluated on cracked data, our findings suggest its potential to improve the performance of other binary classification image segmentation problems.

Biomedical Entity Linking(BEL) is the task of linking biomedical mentions in natural language corpora such as diseases and drugs to standard entities in a given knowledge base. The same biomedical entity can have multiple mentions, including synonyms, morphological variations and names with different word order. Thus, making predictions for each mention with an insufficient context in a single biomedical document is challenging, especially when mentions or linked entities are unseen during training. This paper proposes an inference method for biomedical entity linking based on the heterogeneous graph constructed on multiple documents. We first design a joint representation learning method and compute mention-mention and mention-entity similarity in a unified semantic space. Based on them, we utilize the mutual nearest neighbors relationship between mentions and the relationship between mention and entity to construct a heterogeneous graph. Finally, we apply a clustering-based method to make linking predictions, which associates each mention in the documents with a unique entity. Extensive experiments on three biomedical entity linking benchmarks (MedMentions, BC5CDR and NCBI) demonstrate that our method outperforms other state-of-the-art entity linking models.

Binary medical image segmentation plays a pivotal role in the diagnosis and treatment of a wide range of diseases. However, the performance of the segmentation model is closely related to the choice of the binarization threshold (default 0.5), which is used to binarize the output probability mask. In this paper, we introduce an innovative multi-task learning framework featuring an Adaptive Thresholding Module (ATM) designed to predict the optimal threshold for each image. Within this multi-task learning framework, the segmentation task is divided into two distinct subtasks. The first subtask focuses on the original segmentation task to output the probabilistic mask. Simultaneously, the second subtask leverages spatial features extracted from the segmentation network, with ATM learning and applying these features in a regression task to derive the optimal threshold for each image. Subsequently, a binarization process is enacted using these optimal thresholds, leading to a marked improvement in segmentation accuracy. The crux of ATM’s contribution to enhanced segmentation accuracy lies in its ability to optimize the binarization process, striking a well-balanced equilibrium between the labels of true positive and false positive. We integrated ATM into various medical segmentation models and subjected it to evaluation on datasets encompassing diverse binarized medical image patterns. The results underscore the effectiveness of ATM in elevating the accuracy of pre-existing medical segmentation models.

Document-level relation extraction (DocRE) is an important task in natural language processing, with applications in knowledge graph construction, question answering, and biomedical text analysis. However, existing approaches to DocRE have limitations in predicting relations between entities using fixed entity representations, which can lead to inaccurate results. In this paper, we propose a novel DocRE model that addresses these limitations by using a relation-specific entity representation method and evidence sentence augmentation. Our model uses evidence sentence augmentation to identify top-k evidence sentences for each relation and a relation-specific entity representation method that aggregates the importance of entity mentions using an attention mechanism. These two components work together to capture the context of each entity mention in relation to the specific relation being predicted and select evidence sentences that support accurate relation identification. Finally, we re-predicts entity relations based on the evidence sentences, called relationship reordering module. This module re-predicts entity relationships based on the predicted set of evidence sentences to form k sets of relationship predictions, and then averages these k+1 sets of results to obtain the final relationship predictions. Experimental results on the DocRED dataset demonstrate that our proposed model achieves an F1 score of 62.84% and an lgn F1 score of 60.79%, outperforming state-of-the-art methods.

Document-level relation extraction (DocRE) is a more challenging task for which multi-label and multi-entity problems need to be resolved effectively than its sentence-level counterpart. It aims at extracting relationships between two entities at once while taking into account significant cross-sentence features and long-distance semantic representation. In this paper, we propose a self-supervised commonsense-enhanced DocRE model, called CommDRE, without external knowledge. First, we introduce self-supervised learning to represent the commonsense knowledge of each entity in an entity pair. Second, we convert the cross-sentence entity pairs into anonymous entity pairs with a coreference commonsense alternative. Finally, we perform semantic relation representation learning on the anonymous entity pairs and automatically convert them into target entity pairs. Experimental results show that it performs significantly better than strong baselines by 2.76% F1, and commonsense knowledge has an important contribution to the DocRE through the ablation study.

Current state-of-the-art semantic segmentation methods usually require high computational resources for accurate segmentation. Knowledge distillation has been one promising way to achieve a good trade-off between accuracy and efficiency. However, current distillation methods focus on transferring the spatial relations and ignore the multi-scale context interaction. This paper proposes one novel pixel- region relation distillation (PPRD) to transfer the multi-scale pixel-region relation (PRR) from the teacher to the student. We get the multi-scale regions with pyramid pooling and characterize the multi-scale PRR between the feature and the multi-scale regions. Transferring such PRR from the teacher to the student is beneficial for the student to mimic the teacher better in terms of multi-scale context interaction. Experimental results on two challenging datasets, Cityscapes and Pascal VOC 2012, show that the proposed approach outperforms state-of-the-art distillation methods.

Knowledge distillation has been widely applied in semantic segmentation to reduce the model size and computational complexity. The prior knowledge distillation methods for semantic segmentation mainly focus on transferring the spatial relation knowledge, neglecting to transfer the channel correlation knowledge in the feature space, which is vital for semantic segmentation. We propose a novel Channel Correlation Distillation (CCD) method for semantic segmentation to solve this issue. The correlation between channels tells how likely these channels belong to the same categories. We force the student to mimic the teacher by minimizing the distance between the channel correlation maps of the student and the teacher. Furthermore, we propose the multi-scale discriminators to sufficiently distinguish the multi-scale differences between the teacher and student segmentation outputs. Extensive experiments on three popular datasets: Cityscapes, CamVid, and Pascal VOC 2012 validate the superiority of our CCD. Experimental results show that our CCD could consistently improve the state-of-the-art methods with various network structures for semantic segmentation.

The Semantic Internet of Things (SIoT) is the extension of the Internet of Things (IoT) and the Semantic Web, which aims to build an interoperable collaborative system to solve the heterogeneous problems in the IoT. However, the SIoT has the characteristics of both the IoT and the Semantic Web environment, and the corresponding semantic data present many new data features. In this article, we analyze the characteristics of semantic data and propose the concept of a uniform knowledge graph (UKG), allowing us to be applied to the environment of the SIoT better. Here, we design a semantic collaboration method based on a UKG. It can take the UKG as the form of knowledge organization and representation, and provide a useful data basis for semantic collaboration by constructing the semantic links to complete semantic relation between different data sets, to achieve the semantic collaboration in the SIoT. Our experiments show that the proposed method can analyze and understand the semantics of user requirements better and provide more satisfactory outcomes.