Abstract Drug–drug interactions (DDIs) are a crucial research focus in clinical pharmacology and public health. DDIs can lead to reduced drug efficacy or increased adverse reactions, making the effective identification and understanding of drug interactions essential for patient safety and treatment outcomes. With the rapid growth of biomedical literature, automated methods for extracting DDI information have become increasingly necessary. In this paper, we propose BLRG, a novel model that uniquely integrates BioBERT, long short-term memory (LSTM), and relational graph convolutional network (R-GCN) to extract complex DDIs. This combination allows the model to effectively capture both semantic and relational features, outperforming existing methods in handling intricate dependencies in biomedical texts. Specifically, our approach begins by utilizing the BioBERT model to capture deep contextual features of sentences, extracting their semantic information. Following this, an LSTM network processes the sequential features of the sentence to model its contextual dependencies. Finally, an R-GCN is applied to identify and interpret the relationships between drug entities within the sentence, accurately capturing DDI information. Experimental results demonstrate that our model significantly outperforms current state-of-the-art methods across standard datasets, showcasing its effectiveness and potential in complex DDI extraction tasks. Our code and data are publicly available at: https://github.com/Hero-Legend/BLRG.

Abstract The Multimodal Named Entity Recognition (MNER) task enhances the text representations and improves the accuracy and robustness of named entity recognition by leveraging visual information from images. However, previous methods have two limitations: (i) the semantic mismatch between text and image modalities makes it challenging to establish accurate internal connections between words and visual representations. Besides, the limited number of characters in social media posts leads to semantic and contextual ambiguity, further exacerbating the semantic mismatch between modalities. (ii) Existing methods employ cross-modal attention mechanisms to facilitate interaction and fusion between different modalities, overlooking fine-grained correspondences between semantic units of text and images. To alleviate these issues, we propose a graph neural network approach for MNER (GNN-MNER), which promotes fine-grained alignment and interaction between semantic units of different modalities. Specifically, to mitigate the issue of semantic mismatch between modalities, we construct corresponding graph structures for text and images, and leverage graph convolutional networks to augment text and visual representations. For the second issue, we propose a multimodal interaction graph to explicitly represent the fine-grained semantic correspondences between text and visual objects. Based on this graph, we implement deep-level feature fusion between modalities utilizing graph attention networks. Compared with existing methods, our approach is the first to extend graph deep learning throughout the MNER task. Extensive experiments on the Twitter multimodal datasets validate the effectiveness of our GNN-MNER.

Data classification storage has emerged as an effective strategy, harnessing the diverse performance attributes of storage devices and orchestrating a harmonious equilibrium between energy consumption, cost considerations, and user accessibility. As research on emerging storage media (e.g. Non-Volatile Memory (NVM)) delves deeper, in scenarios characterized by dynamically evolving storage demands, conventional paradigms of rigid classification strategy and Solid-State Drive (SSD) and Hard Disk Drive (HDD) storage architectures fall short of addressing such complex situations. In this paper, we propose an effective data classification storage method using text seasonal features based on the traditional access frequency analysis strategy. First, to procure richer semantic information, we employ external knowledge actualizing the short-text feature expansion. Then, we leverage the ensemble learning stacking method optimized models to improve the accuracy of data classification based on seasonal features. Additionally, following the seasonal feature, we further classify the data into hot, warm, and cold and place them separately on the NVM, SSD, and HDD, which conserves storage energy consumption and operational costs while ensuring the quality of user access. The experimental results demonstrate that data classification accuracy can reach more than 95.10%, and the energy consumption and operating cost can be reduced by more than 30.22% and 8.73%, respectively.

With the expansion of the number of users in online social networks, the diversity of users and community characteristics become more prominent. Hypernetwork theory provides a path for characterizing complex relationships in networks. This paper used hypergraph’s hyperedges to represent the community relationship between users, and created an online social hypernetwork information dissemination model (UHIR model) based on user and information attributes by combining the hypernetwork model with the SEIR model. Through this model, this article simulated and analyzed the dynamic process and laws of information dissemination under different network structures, and studied the influence of user influence, confidence, interest value, and information timeliness of the process. The simulation results show that this model can accurately describe the information dissemination trend and process in the real online social network. This work extends a new research direction of information dissemination in hypernetworks and contributes to the in-depth study of more complex information dissemination mechanisms.

This paper investigates secrecy efficiency (SE) optimization in a friendly full-duplex (FD) decode- and-forward (DF) relay network with a passive eavesdropper. Targeting on SE maximization, the power allocation is optimized subject to the total power and minimum secrecy rate constraints adapting to the assumption of unknown eavesdropper's channel state information (CSI). By exploiting the properties of fractional programming (FP) and Difference of Convex functions (DC) programming, the resulting nonconvex optimization problem can be relaxed into a more tractable equivalent problem. Simulation results demonstrate that our proposed scheme can reach a better trade-off between security performance and energy consumption.

This paper addresses the problem of clustering a very large number of photos (i.e. hundreds of millions a day) in a stream into millions of clusters. This is particularly important as the popularity of photo sharing websites, such as Facebook, Google, and Instagram. Given large number of photos available online, how to efficiently organize them is an open problem. To address this problem, we propose to cluster the binary hash codes of a large number of photos into binary cluster centers. We present a fast binary k-means algorithm that works directly on the similarity-preserving hashes of images and clusters them into binary centers on which we can build hash indexes to speedup computation. The proposed method is capable of clustering millions of photos on a single machine in a few minutes. We show that this approach is usually several magnitude faster than standard k-means and produces comparable clustering accuracy. In addition, we propose an online clustering method based on binary k-means that is capable of clustering large photo stream on a single machine, and show applications to spam detection and trending photo discovery.

Binary embedding of high-dimensional data requires long codes to preserve the discriminative power of the input space. Traditional binary coding methods often suffer from very high computation and storage costs in such a scenario. To address this problem, we propose Circulant Binary Embedding (CBE) which generates binary codes by projecting the data with a circulant matrix. The circulant structure enables the use of Fast Fourier Transformation to speed up the computation. Compared to methods that use unstructured matrices, the proposed method improves the time complexity from \mathcalO(d^2) to \mathcalO(d\logd), and the space complexity from \mathcalO(d^2) to \mathcalO(d) where d is the input dimensionality. We also propose a novel time-frequency alternating optimization to learn data-dependent circulant projections, which alternatively minimizes the objective in original and Fourier domains. We show by extensive experiments that the proposed approach gives much better performance than the state-of-the-art approaches for fixed time, and provides much faster computation with no performance degradation for fixed number of bits.

In large-scale query-by-example retrieval, embedding image signatures in a binary space offers two benefits: data compression and search efficiency. While most embedding algorithms binarize both query and database signatures, it has been noted that this is not strictly a requirement. Indeed, asymmetric schemes that binarize the database signatures but not the query still enjoy the same two benefits but may provide superior accuracy. In this work, we propose two general asymmetric distances that are applicable to a wide variety of embedding techniques including locality sensitive hashing (LSH), locality sensitive binary codes (LSBC), spectral hashing (SH), PCA embedding (PCAE), PCAE with random rotations (PCAE-RR), and PCAE with iterative quantization (PCAE-ITQ). We experiment on four public benchmarks containing up to 1M images and show that the proposed asymmetric distances consistently lead to large improvements over the symmetric Hamming distance for all binary embedding techniques.

Recent advances in visual recognition indicate that to achieve good retrieval and classification accuracy on large-scale datasets like Image Net, extremely high-dimensional visual descriptors, e.g., Fisher Vectors, are needed. We present a novel method for converting such descriptors to compact similarity-preserving binary codes that exploits their natural matrix structure to reduce their dimensionality using compact bilinear projections instead of a single large projection matrix. This method achieves comparable retrieval and classification accuracy to the original descriptors and to the state-of-the-art Product Quantization approach while having orders of magnitude faster code generation time and smaller memory footprint.

This paper addresses the problem of learning similarity-preserving binary codes for efficient similarity search in large-scale image collections. We formulate this problem in terms of finding a rotation of zero-centered data so as to minimize the quantization error of mapping this data to the vertices of a zero-centered binary hypercube, and propose a simple and efficient alternating minimization algorithm to accomplish this task. This algorithm, dubbed iterative quantization (ITQ), has connections to multiclass spectral clustering and to the orthogonal Procrustes problem, and it can be used both with unsupervised data embeddings such as PCA and supervised embeddings such as canonical correlation analysis (CCA). The resulting binary codes significantly outperform several other state-of-the-art methods. We also show that further performance improvements can result from transforming the data with a nonlinear kernel mapping prior to PCA or CCA. Finally, we demonstrate an application of ITQ to learning binary attributes or "classemes" on the ImageNet data set.

This paper focuses on the problem of learning binary embeddings for efficient retrieval of high-dimensional non-negative data. Such data typically arises in a large number of vision and text applications where counts or frequencies are used as features. Also, cosine distance is commonly used as a measure of dissimilarity between such vectors. In this work, we introduce a novel spherical quantization scheme to generate binary embedding of such data and analyze its properties. The number of quantization landmarks in this scheme grows exponentially with data dimensionality resulting in low-distortion quantization. We propose a very efficient method for computing the binary embedding using such large number of landmarks. Further, a linear transformation is learned to minimize the quantization error by adapting the method to the input data resulting in improved embedding. Experiments on image and text retrieval applications show superior performance of the proposed method over other existing state-of-the-art methods.

This paper addresses the problem of learning similarity-preserving binary codes for efficient retrieval in large-scale image collections. We propose a simple and efficient alternating minimization scheme for finding a rotation of zero-centered data so as to minimize the quantization error of mapping this data to the vertices of a zero-centered binary hypercube. This method, dubbed iterative quantization (ITQ), has connections to multi-class spectral clustering and to the orthogonal Procrustes problem, and it can be used both with unsupervised data embeddings such as PCA and supervised embeddings such as canonical correlation analysis (CCA). Our experiments show that the resulting binary coding schemes decisively outperform several other state-of-the-art methods.

This paper presents a comparative evaluation of feature embeddings for classification and ranking in large-scale Internet image datasets. We follow a popular framework for scalable visual learning, in which the data is first transformed by a nonlinear embedding and then an efficient linear classifier is trained in the resulting space. Our study includes data-dependent embeddings inspired by the semi-supervised learning literature, and data-independent ones based on approximating specific kernels (such as the Gaussian kernel for GIST features and the histogram intersection kernel for bags of words). Perhaps surprisingly, we find that data-dependent embeddings, despite being computed from large amounts of unlabeled data, do not have any advantage over data-independent ones in the regime of scarce labeled data. On the other hand, we find that several data-dependent embeddings are competitive with popular data-independent choices for large-scale classification.

In the recent few years, web mining has become a hotspot of data mining with the development of Internet. Web pages classification is one of the essential techniques for web mining since classifying web pages of an interesting class is often the first step of mining the web. The high dimensional text vocabulary space is one of the main challenges of web pages. In this paper, we study the capabilities of Bayesian classifiers for web pages categorization. Several feature selection techniques, such as Chi Squared, Information Gain and Gain Ratio are used for selecting relevant words in web pages. Results on benchmark dataset show that the performances of Aggregating One-Dependence Estimators (AODE) and Hidden Naive Bayes (HNB) are both more competitive than other traditional methods.

Traditional linear discriminant analysis (LDA) is a popular dimensionality reduction method which preserve class separability. The method needs the labeled data to train. However in real worlds, the labeled training examples are very few but there are sufficient unlabeled data examples, so some former work (SDA) has made use the unlabeled training examples to do dimensionality reduction. But sometimes, there exits another kind of domain knowledge: the instances level constraints. In this paper, we consider the case when there are some useful instance level constraints. We propose a novel algorithm semi-supervised discriminant analyze with constraints (SDAC) which use three kinds of data: very few labeled data examples, sufficient unlabeled data examples and the instance level constraints. Our algorithm can be viewed as a constraint extension of traditional SDA algorithm. Experiments have been presented for semi-supervised classification tasks and have shown the effectiveness of our algorithm.

In real world applications, there are great many of DNA expressed microarray data, many supervised classification algorithms such as decision tree, KNN and SVM in the machine learning field have been introduced for microarray data classification. However, in real worlds, the labeled examples, especially gene expression data examples are often very difficult and expensive to obtain. The traditional supervised methods can not work well when lack of training examples. So in this paper, we propose to use the semi-supervised learning algorithms which learning with both labeled and unlabeled data to do classification for microarray data. We perform experiments on four public microarray data sets and the results showed the semi-supervised method holds a much higher classification accuracy than the supervised methods and is much more stable when the labeled examples are very few.

In this paper, we propose a novel semi-supervised algorithm, which works under a two-view setting. Our algorithm, named Kernel Canonical Component Analysis Graph (KC-GRAPH), can effectively enhance the performance and the parameter stability of traditional graph-based semi-supervised algorithms by taking the advantage of two views using Kernel Canonical Component Analysis (KCCA). Experiments have been presented for semi-supervised classification tasks, and have shown that our KC-GRAPH algorithm stays a high classification accuracy and is much more stable than the former algorithms. We also noticed that our algorithm holds very good parameter stability.

Recently increasing interests of applying or developing specialized machine learning techniques have attracted many researchers in the intrusion detection community. Existing research work show: the supervised algorithms deteriorates signifycantly if unknown attacks are present in the test data; the unsupervised algorithms exhibit no significant difference in performance between known and unknown attacks but their performances are not that satisfying. In this contribution, we propose two semi-supervised classification methods, Spectral Graph Transducer and Gaussian Fields Approach, to detect unknown attacks and one semi-supervised clustering method—MPCK-means to improve the performances of the traditional purely unsupervised clustering methods. Our empirical study shows that performances of semi-supervised classification methods are much better than those of supervised classifiers, and semi-supervised clustering method can improve purely unsupervised clustering methods markedly.

In real worlds applications, some former research papers have shown that manifold learning tries to discover the non-linear low-dimensional data manifold from a high-dimensional space. Many natural images and the face images are believed to be sampled from a manifold. In this paper, we try to investigate whether discovering such manifold can aid the semi-supervised learning algorithms. We propose a novel graph-based learning algorithm locality preserving graph-based semi-supervised method (LLGSM), which firstly use both labeled and unlabeled examples as unlabeled to discover the manifolds of the data samples and then use the projected labeled examples together with projected unlabeled ones to do classification. Experiments performed on some public image data sets have demonstrated the effectiveness of our algorithm.