Compared to traditional Computed Tomography (CT) scans and floatation catheters, chest X-ray offers an efficient, safe and timely examination paradigm, with broader range of scenarios (including intensive care units), for the detection of Pulmonary Arterial Hypertension (PAH). However, it is difficult to learn the variable radiological features of PAH from X-rays due to its low resolution and low contrast. To address the above issues, we propose a diversified features learning framework to fully explore the PAH-related representation from chest X-ray. We first employ a Chest Feature Enhancement Attention (CFEA) module to enhance the initial feature representation. Then, we employ the Deep Temporal Anti-Interference Metric Learning (TAIML) module to fully explore the PAH-related features. We incorporate the information on the temporal evolution of patients’ conditions. Specifically, a patient x , after undergoing treatment, may exhibit two possible states: x + (ill) and x − (cured). Therefore, we can define the distance d ( x , x + ) as the intra-class structural distance, and the distance d ( x , x − ) as the inter-class safe distance. Unlike existing metric learning, we adopt a new strategy: we push positive samples towards negative samples, but ensure distance between them is no less than d ( x , x − ) , thereby enhancing intra-class diversity while maintaining discriminability. Meanwhile, we ensure that the distance between positive samples is greater than d ( x , x + ) , thereby preserving the intra-class structure. Through these two steps, we can learn a diversified but discriminative representation of PAH. Comprehensive experiments showed the our model achieved an impressive accuracy of 86.27 % and an AUC of 0.857 in identifying PAH patients. The code is available at https://github.com/zgfdmn/PAH .

Ubiquitous connectivity is a key 6G usage scenario, in which large-scale sensing systems deployed in remote and underserved regions must deliver heterogeneous sensing data under stringent energy budgets and deadline constraints. This paper presents EcoPath, a two-tier data aggregation framework for clustered large-scale sensor networks. EcoPath separates low-power intra-cluster collection from a high-rate multi-interface backhaul operated by cluster heads, where Multipath QUIC (MPQUIC) can be practically deployed to exploit path diversity. At the cluster head, EcoPath jointly integrates (i) a deadline-aware bundling controller that aggregates sensor frames into MTU-bounded bundles to amortize protocol overhead while bounding additional waiting time, and (ii) a robust multi-path scheduler that prioritizes packets using Weighted Earliest- Deadline-First (W-EDF) with fairness protection and selects backhaul paths via a stability-aware quality metric with hysteresis to avoid flapping under time-varying links. We further formulate an explicit energy–timeliness optimization and show how its outputs parameterize the online bundling and scheduling policies. Extensive simulations with realistic wireless effects, together with baselines and ablations, demonstrate that EcoPath improves energy efficiency and deadline satisfaction for large-scale aggregation.

Cross-domain label propagation (LP) faces two main challenges: 1) learning domain-invariant and 2) discriminative feature representations and obtaining high-confidence predicted labels. The distribution differences between domains can make labels difficult to propagate across domains. Low-quality labels can distort the modeling process associated with label-induced loss, resulting in decreased performance. We propose a novel cross-domain image classification method, namely, robust LP and graph embedding (RLPGE). We introduce a nuclear norm maximization constraint in order to make the predicted labels more diverse in categories while preserving their discriminability. The graph embedding process brings two nearby same-class samples close in the embedding subspace, ensuring domain invariance and local discriminability of the embedded features. For optimal graph learning, we simultaneously optimize the cross-domain graph and two intradomain graphs using both features and labels, enhancing their local discriminability and robustness to feature noise. We conducted comprehensive experiments on four cross-domain image classification datasets. The results demonstrate that our proposed RLPGE method outperforming some state-of-the-art approaches

One of the most popular methods for analyzing the robustness of 3D Deep Neural Networks (DNNs) is the transfer-based adversarial attack method, as it allows to analyze the robustness of an unknown model by generating an adversarial point cloud on an alternative model. However, the adversarial point clouds generated by current methods may overfit the surrogate models that generated them, thus limiting their performance in transfer attacks against different target 3D classifiers. To enhance the transferability of the adversarial point cloud, we propose in this letter an adversarial attack method by Initializing the Transferable Adversarial Noise, which named asITAN. Specifically, we pre-train on the training set a generator capable of generating the adversarial noise with transferability and diversity, and then the noise generated by the generator serves as the initial adversarial noise to be integrated into the iterations of the attack. Extensive experiments on well-recognized benchmark datasets demonstrate that the adversarial point clouds generated by the proposed ITAN could be effectively transferred across unknown 3D classifiers.

Feature selection aims to select an optimal minimal feature subset from the original datasets and has become an indispensable preprocessing component before data mining and machine learning, especially in the era of big data. However, features may be generated dynamically and arrive individually over time in practice, which we call streaming features. Most existing streaming feature selection methods assume that all dynamically generated features are the same type or assume we can know the feature type for each new arriving feature in advance, but this is unreasonable and unrealistic. Therefore, this paper first studies a practical issue of Online Heterogeneous Streaming Feature Selection without the feature type information before learning, named OHSFS. Specifically, we first model the streaming feature selection issue as a minimax problem. Then, in terms of MIC (Maximal Information Coefficient), we derive a new metric$MIC_{Gain}$to determine whether a new streaming feature should be selected. To speed up the efficiency of OHSFS, we present the metric$MIC_{Cor}$that can directly discard low correlation features. Finally, extensive experimental results indicate the effectiveness of OHSFS. Moreover, OHSFS is nonparametric and does not need to know the feature type before learning, which aligns with practical application needs.

Recent research has demonstrated that recommendation systems exhibit vulnerability under data poisoning attacks. The primary process of data poisoning attacks involves generating malicious data (i.e., fake users) through surrogate models and injecting the malicious data into the target models’ datasets, thereby manipulating the output results of the target models. However, current methods generating fake users based on gradient descent may cause them to fall into undesired local minimum in the loss landscape and overfitting to the surrogate model, thus limiting the performance of attacking other recommendation models. To address this problem, we propose the reverse optimization algorithm (ReOP), which utilizes the reverse direction of optimization to update fake users, enabling them to steer clear of sharp local minimum in loss landscape and navigate towards the flat local minimum. ReOP makes fake users less sensitive to model changes, alleviates their overfitting to the surrogate model, and thus significantly improves the transferability of fake users. Experimental results demonstrate that ReOP surpasses the state-of-the-art baseline methods, effectively generating fake users with significant attack effects on various target models.

The explosion of data volume has gradually transformed big data processing from the static batch mode to the online streaming model. Streaming data can be divided into instance streams (feature space remains fixed while instances increase over time), feature streams (instance space is fixed while features arrive over time), or both. Generally, online streaming data learning has two main challenges: infinite length and concept changing. Recently, feature stream learning has received much attention. However, existing feature stream learning methods focus on feature selection or classification but ignore the concept changing over time. To the best of our knowledge, this is the first work that studies concept evolution detection over feature streams. Specifically, we first give the formal definition of concept evolution over feature streams, which include three different types: concept emerging, concept drift, and concept forgetting. Then, we design a novel framework to detect the concept evolution over feature streams that consists of a sliding window, an improved density peak-based clustering algorithm, and a weighted bipartite graph-based concept detecting method. Extensive experiments have been conducted on several synthetic and high-dimensional datasets to indicate our new method’s ability to cluster and detect concept evolution over feature streams.

Undersampling is one of the most popular techniques for dealing with class-imbalance problems. Various undersampling methods have emerged over the past few decades. Each of them exhibits the superiority in some scenarios. However, selecting representative majority-class samples such that the structures of the selected groups are maintained according to the underlying imbalanced distribution remains a challenge. For this purpose, this paper proposes Spatial Distribution-based UnderSampling (SDUS) for imbalanced learning. SDUS uses a supervised constructive process to learn majority-class local patterns in terms of sphere neighborhoods (SPN). Two sample selection strategies, specifically, a top-down strategy and a bottom-up strategy, are proposed for maintaining the distribution pattern of original data in selecting majority-class sample subsets from different perspectives. SDUS introduces an ensemble technique that improves learning performance by utilizing the diversity caused by the randomness of the local-pattern learning process. Numerical experiments on 38 typical datasets from KEEL repository and 13 state-of-the-art comparison methods demonstrate the effectiveness of SDUS in maintaining the underlying distribution characteristics for imbalanced undersampling.

Multi-class imbalanced problem widely exists in real-life applications and has been a challenging issue. Existing sampling methods including decomposition approaches and dedicated approaches have limitations in handling the complex mutual relationships along with data difficulty factors. Actually, the relative minorities are critical in mutual relationship, and the data difficulty factors are harmful for these minority classes. In this paper, we propose SHSampler, a similarity-based hybrid sampling to combat the mutuality by addressing data difficulty factors in multi-class imbalanced data. Specifically, SHSampler firstly utilizes a sample similarity and dissimilarity estimation to identify data difficulty factors. Then, SHSampler conducts a relative majority weakening undersampling and a relative minority strengthening oversampling to reduce the negative impact of data difficulty factors and highlight the importance of the minorities. Extensive experiments over 20 typical datasets demonstrate the superiority of SHSampler in terms of MAUC and mGM when compared with 6 state-of-the-art methods.

Feature selection is one of the core concepts in machine learning, which hugely impacts the model’s performance. For some real-world applications, features may exist in a stream mode that arrives one by one over time, while we cannot know the exact number of features before learning. Online streaming feature selection aims at selecting optimal stream features at each timestamp on the fly. Without the global information of the entire feature space, most of the existing methods select stream features in terms of individual feature information or the comparison of features in pairs. This article proposes a new online scalable streaming feature selection framework from the dynamic decision perspective that is scalable on running time and selected features by dynamic threshold adjustment. Regarding the philosophy of “Thinking-in-Threes”, we classify each new arrival feature as selecting, discarding, or delaying, aiming at minimizing the overall decision risks. With the dynamic updating of global statistical information, we add the selecting features into the candidate feature subset, ignore the discarding features, cache the delaying features into the undetermined feature subset, and wait for more information. Meanwhile, we perform the redundancy analysis for the candidate features and uncertainty analysis for the undetermined features. Extensive experiments on eleven real-world datasets demonstrate the efficiency and scalability of our new framework compared with state-of-the-art algorithms.