Intelligent Data Analysis: An International Journal

Multi-label image classification aims to predict a set of labels that are present in an image. The key challenge of multi-label image classification lies in two aspects: modeling label correlations and utilizing spatial information. However, the existing approaches mainly calculate the correlation between labels according to co-occurrence among them. While the result is easily affected by the label noise and occasional co-occurrences. In addition, some works try to model the correlation between labels and spatial features, but the correlation among labels is not fully considered to model the spatial relationships among features. To address the above issues, we propose a novel cross-modality semantic guidance-based framework for multi-label image classification, namely CMSG. First, we design a semantic-guided attention (SGA) module, which applies the label correlation matrix to guide the learning of class-specific features, which implicitly models semantic correlations among labels. Second, we design a spatial-aware attention (SAA) module to extract high-level semantic-aware spatial features based on class-specific features obtained from the SGA module. The experiments carried out on three benchmark datasets demonstrate that our proposed method outperforms existing state-of-the-art algorithms on multi-label image classification.

There are two mainstream strategies for image-text matching at present. The one, termed as joint embedding learning, aims to model the semantic information of both image and sentence in a shared feature subspace, which facilitates the measurement of semantic similarity but only focuses on global alignment relationship. To explore the local semantic relationship more fully, the other one, termed as metric learning, aims to learn a complex similarity function to directly output score of each image-text pair. However, it significantly suffers from more computation burden at retrieval stage. In this paper, we propose a hierarchically joint embedding model to incorporate the local semantic relationship into a joint embedding learning framework. The proposed method learns the shared local and global embedding spaces simultaneously, and models the joint local embedding space with respect to specific local similarity labels which are easy to access from the lexical information of corpus. Unlike the methods based on metric learning, we can prepare the fixed representations of both images and sentences by concatenating the normalized local and global representations, which makes it feasible to perform the efficient retrieval. And experiments show that the proposed model can achieve competitive performance when compared to the existing joint embedding learning models on two publicly available datasets Flickr30k and MS-COCO.

Nowadays, the idea of active learning is gradually adopted to assist domain adaptation. However, due to the existence of domain shift, the traditional active learning methods originating from semi-supervised scenarios can not be directly applied to domain adaptation. To solve the problem, active domain adaptation is proposed as a new domain adaptation paradigm, which aims to improve the performance of the model by annotating a small amount of target domain samples. In this regard, we propose an active domain adaptation method named Boosting Active Domain Adaptation with Exploration of Samples (BADA), dividing Active DA into two related issues: sample selection and sample utilization. We design the instability selection criterion based on predictive consistency and the diversity selection criterion. For the remaining unlabeled samples, we design a self-training framework, which screens out reliable samples and unreliable samples through the sample screening mechanism similar to selection criteria. And we adopt respective loss functions for reliable samples and unreliable samples. Experiments show that BADA remarkably outperforms previous active learning methods and Active DA methods on several domain adaptation datasets.

Most methods for multi-domain adaptive neural machine translation (NMT) currently rely on mixing data from multiple domains in a single model to achieve multi-domain translation. However, this mixing can lead to imbalanced training data, causing the model to focus on training for the large-scale general domain while ignoring the scarce resources of specific domains, resulting in a decrease in translation performance. In this paper, we propose a multi-domain adaptive NMT method based on Domain Data Balancer (DDB) to address the problems of imbalanced data caused by simple fine-tuning. By adding DDB to the Transformer model, we adaptively learn the sampling distribution of each group of training data, replace the maximum likelihood estimation criterion with empirical risk minimization training, and introduce a reward-based iterative update of the bilevel optimizer based on reinforcement learning. Experimental results show that the proposed method improves the baseline model by an average of 1.55 and 0.14 BLEU (Bilingual Evaluation Understudy) scores respectively in English-German and Chinese-English multi-domain NMT.

While increasingly complex algorithms are being developed for graph classification in highly-structured domains, such as image processing and climate forecasting, they often lead to over-fitting and inefficiency when applied to human interaction networks where the confluence of cooperation, conflict, and evolutionary pressures produces chaotic environments. We propose a graph transformation approach for efficient classification in chaotic human systems that is based on game theoretic, network theoretic, and chaos theoretic principles. Graph structural properties are compiled into time-series that are then transposed into the frequency domain to offer a dynamic view of the system for classification. We propose a set of benchmark data sets and show through experiments that the approach is efficient and appropriate for many dynamic networks in which agents both compete and cooperate, such as social media networks, stock markets, political campaigns, legislation, and geopolitical events.

Event extraction (EE) is an important natural language processing task. With the passage of time, many powerful and effective models for event extraction tasks have been developed. However, there has been limited research on complex overlapping event extraction. Therefore, we propose a new cascade decoding model: A Joint Learning Framework for Cascade Decoding with Multi-Feature Fusion and Conditional Enhancement for Overlapping Event Extraction. 1) In this model, we introduce a cascade decoding mechanism with multi-feature fusion to better capture the interaction between decoding layers. 2) Additionally, we introduce an enhanced conditional layer normalization (ECLN) mechanism to enhance the interaction between subtasks. Simultaneously, the use of a cascade decoding model effectively addresses the problem of overlapping events. The model successively performs three subtasks, type detection, trigger word extraction and argument extraction. All three subtasks learned together in a framework, and a new conditional normalization mechanism is used to capture dependencies among these subtasks. The experiments are conducted using the overlapping event benchmark, FewFC dataset. The experimental evaluation demonstrates that our model achieves a higher F1 score on the overlapping event extraction task compared to the original overlapping event extraction model.

Recommendation systems are an effective solution to deal with information overload, particularly in the e-commerce sector, in which sequential recommendation is extensively utilized. Sequential recommendations aim to acquire users’ interests and provide accurate recommendations by analyzing users’ historical interaction sequences. To improve recommendation performance, it is vital to take into account the long- and short-term interests of users. Despite significant advancements in this domain, some issues need to be addressed. Conventional sequential recommendation models typically express each item with a uniform embedding, ignoring evolutionary patterns among item attributes, such as category, brand, and price. Moreover, these models often model users’ long- and short-term interests independently, failing to adequately address the issues of interest drift and short-term interest evolution. This study proposes a new model, the Feature-aware Long-Short Interest Evolution Network (FLSIE), to address the above-mentioned issues. Specifically, the model uses explicit feature embedding to represent item attribute information and employs a two-dimensional (2D) attention mechanism to distinguish the significance of individual features in a specific item and the relevance of each item in the interaction sequence. Furthermore, to avoid the issue of interest drift, the model employs a long-term interest guidance mechanism to enhance the representation of short-term interest and adopts a gated recurrent unit with attentional update gate to model the dynamic evolution of users’ short-term interest. Experimental results indicate that our presented model outperforms existing methods on three real-world datasets.

Accurate and reliable prediction of Alzheimer’s disease (AD) progression is crucial for effective interventions and treatment to delay its onset. Recently, deep learning models for AD progression achieve excellent predictive accuracy. However, their predictions lack reliability due to the non-calibration defects, that affects their recognition and acceptance. To address this issue, this paper proposes a temporal attention-aware evidential recurrent network for trustworthy prediction of AD progression. Specifically, evidential recurrent network explicitly models uncertainty of the output and converts it into a reliability measure for trustworthy AD progression prediction. Furthermore, considering that the actual scenario of AD progression prediction frequently relies on historical longitudinal data, we introduce temporal attention into evidential recurrent network, which improves predictive performance. We demonstrate the proposed model on the TADPOLE dataset. For predictive performance, the proposed model achieves mAUC of 0.943 and BCA of 0.881, which is comparable to the SOTA model MinimalRNN. More importantly, the proposed model provides reliability measures of the predicted results through uncertainty estimation and the ECE of the method on the TADPOLE dataset is 0.101, which is much lower than the SOTA model at 0.147, indicating that the proposed model can provide important decision-making support for risk-sensitive prediction of AD progression.

Deformable medical image registration is a fundamental and critical task in medical image analysis. Recently, deep learning-based methods have rapidly developed and have shown impressive results in deformable image registration. However, existing approaches still suffer from limitations in registration accuracy or generalization performance. To address these challenges, in this paper, we propose a pure convolutional neural network module (CVTF) to implement hierarchical transformers and enhance the registration performance of medical images. CVTF has a larger convolutional kernel, providing a larger global effective receptive field, which can improve the network’s ability to capture long-range dependencies. In addition, we introduce the spatial interaction attention (SIA) module to compute the interrelationship between the target feature pixel points and all other points in the feature map. This helps to improve the semantic understanding of the model by emphasizing important features and suppressing irrelevant ones. Based on the proposed CVTF and SIA, we construct a novel registration framework named PCTNet. We applied PCTNet to generate displacement fields and register medical images, and we conducted extensive experiments and validation on two public datasets, OASIS and LPBA40. The experimental results demonstrate the effectiveness and generality of our method, showing significant improvements in registration accuracy and generalization performance compared to existing methods. Our code has been available at https://github.com/fz852/PCTNet.

Skin lesion segmentation from dermatoscopic images is essential for the diagnosis of skin cancer. However, it is still a challenging task due to the ambiguity of the skin lesions, the irregular shape of the lesions and the presence of various interfering factors. In this paper, we propose a novel Ambiguous Context Enhanced Attention Network (ACEANet) based on the classical encoder-decoder architecture, which is able to accurately and reliably segment a variety of lesions with efficiency. Specifically, a novel Ambiguous Context Enhanced Attention module is embedded in the skip connection to augment the ambiguous boundary information. A Dilated Gated Fusion block is employed in the end of the encoding phase, which effectively reduces the loss of spatial location information due to continuous downsampling. In addition, we propose a novel Cascading Global Context Attention to fuse feature information generated by the encoder with features generated by the decoder of the corresponding layer. In order to verify the effectiveness and advantages of the proposed network, we have performed comparative experiments on ISIC2018 dataset and PH2 dataset. Experiments results demonstrate that the proposed model has superior segmentation performance for skin lesions.

Code search, which locates code snippets in large code repositories based on natural language queries entered by developers, has become increasingly popular in the software development process. It has the potential to improve the efficiency of software developers. Recent studies have demonstrated the effectiveness of using deep learning techniques to represent queries and codes accurately for code search. In specific, pre-trained models of programming languages have recently achieved significant progress in code searching. However, we argue that aligning programming and natural languages are crucial as there are two different modalities. Existing pre-train models based approaches for code search do not effectively consider implicit alignments of representations across modalities (inter-modal representation). Moreover, the existing methods do not take into account the consistency constraint of intra-modal representations, making the model ineffective. As a result, we propose a novel code search method that optimizes both intra-modal and inter-modal representation learning. The alignment of the representation between the two modalities is achieved by introducing contrastive learning. Furthermore, the consistency of intra-modal feature representation is constrained by KL-divergence. Our experimental results confirm the model’s effectiveness on seven different test datasets. This paper proposes a code search method that significantly improves existing methods. Our source code is publicly available on GitHub.¹

Among the problems of specifying the style and number of elements of a travel magazine, the problem of generating magazine layout by constraining text, and constraining graph layout remains a complex and unsolved problem. In this paper, we generate layouts of text satisfying constraints via GAN. Due to the complexity and variety of graph designs, we enhance the performance of the discriminator and the generator so that the layouts generated by the generator are more constrained. Add non-corresponding constraint text and real layout pairs to the discriminator to enhance the performance of the discriminator; then add a spatial attention mechanism to the layout encoder to extract the features of the layout and generate high-quality layouts. We demonstrate that the proposed method can generate high-quality layouts of text satisfying the constraints, and we validate the effectiveness of this method through user ratings.

Named Entity Recognition (NER) is an essential task in Natural Language Processing (NLP), and deep learning-based models have shown outstanding performance. However, the effectiveness of deep learning models in NER relies heavily on the quality and quantity of labeled training datasets available. A novel and comprehensive training dataset called SocialNER2.0 is proposed to address this challenge. Based on selected datasets dedicated to different tasks related to NER, the SocialNER2.0 construction process involves data selection, extraction, enrichment, conversion, and balancing steps. The pre-trained BERT (Bidirectional Encoder Representations from Transformers) model is fine-tuned using the proposed dataset. Experimental results highlight the superior performance of the fine-tuned BERT in accurately identifying named entities, demonstrating the SocialNER2.0 dataset’s capacity to provide valuable training data for performing NER in human-produced texts.