The widespread adoption of graph neural networks (GNNs) has brought increased attention to fairness issues related to sensitive attributes, such as gender and race, in practical scenarios. However, this concern remains largely unexplored in the context of graph clustering. Conventional fair graph clustering methods primarily depend on spectral clustering approaches. Meanwhile, we argue that existing graph learning works mainly focus on a single type of fairness, whereas graph clustering should achieve group equality-informed individual fairness. In this paper, we introduce for the first time a fairness-aware framework termed FairGC for deep graph clustering, which integrates the dual objectives of individual and group fairness while maintaining accurate clustering results. Specifically, we construct two views with distinct semantics using Siamese encoders. Then, we apply multi-step random walks on view-specific affinity graphs to capture high-order affinities of node pairs, thereby reformulating the contrastive learning with a focus on individual similarity. Besides, we utilize adversarial learning by making node representations independent of the estimated sensitive attributes to further eliminate group biases of clustering results. Extensive experiments on four benchmarks demonstrate the effectiveness and superiority of our proposed framework FairGC.

Deep neural networks (DNNs) have achieved extensive progress in time series learning. However, they could suffer from performance degradation when it comes to label noise in the real world. Towards this end, this paper studies an underexplored yet realistic problem of noise-resistant time series learning and proposes a novel data-centric approach named Dual Data-centric Separation with Circular Mixup (DREAM) for this problem. The core of our DREAM is to explore and exploit the noisy data from dual data-centric views for reduced overfitting. On the one hand, we assume that samples with similar features share similar labels and infer the pseudo label of each sample using its affinity graph to capture the corresponding pseudo margin. On the other hand, we monitor the optimization status by simulating the mislabeled data to generate flexible criteria for accurate separation of clean and noisy samples. In addition, we leverage circular Mixup to interpolate between clean and noisy samples in the embedding space. These mixed samples are incorporated into a discrepancy-aware consistency learning framework to ensure robust time series representations of all the separated samples. Experimental results on a wide range of publicly accessible datasets reveal the effectiveness of our DREAM.

This paper investigates the task of unsupervised graph domain adaptation, which facilitates the transfer of knowledge from labeled source graphs to unlabeled target graphs. Recent approaches usually utilize graph contrastive learning and pseudo-labeling to learn from unlabeled target data, which could introduce potential biased representations and supervision of target graphs resulting from serious shifts across two domains. Towards this end, we propose a novel framework named Diffusion-guided Unbiased Discriminative Learning (DisCo) for unsupervised graph domain adaptation. The core of our DisCo is to leverage both feature disentanglement and cross-domain diffusion signals to remove the potential biases for target graphs. In particular, we first utilize adversarial feature disentanglement to extract causal features that are orthogonal to domain biases. More importantly, we retrieve the labels of cross-domain source graphs to generate the conditions, which would be utilized to optimize a diffusion model for label denoising. The consistency between pseudo-labels and denoised labels is measured to reduce the potential biases during domain alignment. Extensive experiments on several real-world benchmarks demonstrate that our proposed DisCo consistently outperforms competing state-of-the-art baselines.

Out-of-distribution (OOD) detection has garnered increasing concern for identifying test samples that exhibit a distributional shift from the training dataset in practical deep learning applications. With the significant advancements in graph deep learning for graph representation, graph OOD detection has emerged as a research problem. Graph contrastive learning (GCL) is applied to graph OOD detection due to its capacity for learning discriminative representations in a self-supervised manner, thereby eliminating the need for time-consuming and labor-intensive label information. However, existing methods often neglect the explicit consideration of underlying semantics behind graph data distribution for OOD detection. We argue that simple data augmentations for GCL may risk disrupting the intrinsic graph structure while retaining redundant structural information, which hinders semantic discrimination between graphs. Additionally, Euclidean space embedding struggles to maintain hierarchical structural consistency, making it challenging to meaningfully capture the hierarchical semantic distribution of graph data. In response to these issues, we propose a novel framework termed HGOOD-D, which aims to explore latent semantic hierarchies in hyperbolic space for graph OOD detection. Specifically, we design a bottleneck graph extractor grounded in the information bottleneck (IB) principle, which captures the minimal sufficient information to distinguish graph patterns. Based on this, we introduce hierarchical contrastive learning to capture the hierarchical semantics within graph data distribution. These methods are based on hyperbolic space embedding that can preserve complex inter-relationships in graph hierarchies, thereby mitigating data distortion. Comprehensive evaluations on ten widely used benchmark datasets show that HGOOD-D consistently surpasses current state-of-the-art approaches in graph OOD detection.

This paper studies the problem of graph out-of-distribution generalization, which aims to enhance the performance of graph neural networks (GNNs) under distribution shifts. Existing approaches usually learn graph representations from a casual graph, which may not explicitly utilize environment information explicitly. Furthermore, they could suffer from performance degradation when confusing semantics related to target labels and environments. In this paper, we propose a novel approach named Dual Prompt Learning with Information Bottleneck (DATE) for graph out-of-distribution generalization. The core of our DATE is to utilize dual prompts to extract task-oriented semantics and model distribution shifts, respectively. In particular, we first pre-train a GNN using contrastive learning with pretext tokens introduced. More importantly, we not only introduce a task-oriented prompt based on LLMs to generate environment-invariant representations, but also learn the environment-oriented prompts to simulate subgraphs in different environments. To optimize our prompts, we introduce a graph information bottleneck framework, which minimizes the mutual information between environment-invariant representations and environment semantics with the most semantics preserved. Extensive experiments on various benchmark datasets validate the effectiveness of our DATE against various state-of-the-art approaches.

Time-of-use (ToU) tariffs flexibly offer markedly cheap electricity prices to industrial and residential users during off-peak periods, encouraging them to shift their peak electricity demands in valley periods. Although ToU tariffs play a crucial role in balancing electricity supply and demand, especially in energy-intensive industries, the best trade-off between industrial performance and energy costs has not been well explored. Manufacturing consumes a substantial amount of energy, primarily in the form of electricity, leading to imbalances in power consumption. The flow shop scheduling (FSS) model is one of the most prevalent models in manufacturing. To explore the significant role of ToU tariffs in manufacturing, this study addresses a bi-objective FSS problem under ToU tariffs. The objective is to find the optimal balance between customer satisfaction and total electricity cost. A tight mixed integer programming model is developed to solve this NP-hard problem using business optimizers. On the bases of the problem properties demonstrated in this study, valid inequalities are designed to reduce the solution space of the problem. For small-scale instances, an improved$\varepsilon $-constraint method is presented to find the Pareto front. For medium and large-scale instances, a two-stage fruit fly optimization (TFFO) algorithm is developed to obtain the near Pareto front. Experimental results demonstrate the efficiency and effectiveness of the proposed model and algorithms.Note to Practitioners—Scheduling for complex systems remains a formidable challenge in manufacturing. Energy cost saving is a major objective for all energy-intensive industries. Effective scheduling is crucial for businesses achieving eco-friendly performance, especially under ToU tariffs. This study aims to provide efficient scheduling model and methods that can guide decision-makers in fostering ecological transitions. The$\varepsilon $-constraint method can find globally optimal solutions within given constraints. This situation is particularly beneficial for small-scale production systems requiring high accuracy. The TFFO algorithm can handle complex industrial environments and enhance production efficiency. Additionally, the TFFO algorithm is flexible and extensible, enabling it to be generalized to other production scenarios. Overall, the proposed model and algorithms lay a solid foundation for achieving efficient scheduling under ToU tariffs.

Molecular property prediction plays a crucial role in drug discovery, but is always challenged by the limited number of effective labels. Compared with existing methods, we argue that the auxiliary properties of the molecule and the heterogeneous structure of different property prediction tasks have always been ignored. In this article, we propose a novel framework termed Meta-DREAM for few-shot molecular property prediction, which tailors to learning the transferable knowledge within different clusters of tasks. Specifically, we first construct a heterogeneous molecule relation graph (HMRG) with molecule-property and molecule-molecule relations to utilize many-to-many correlations between properties and molecules. The meta-learning episode can, then, be reformulated as a subgraph of HMRG. Next, we propose a disentangled graph encoder to explicitly discriminate the underlying factors of the task. In addition, we introduce a soft clustering module to group each factorized task representation into appropriate clusters and preserve knowledge generalization within a cluster and customization among clusters. In this way, each disentangled factor serves as a cluster-aware parameter gate for the task-specific meta-learner. Extensive experiments on five commonly used molecular datasets show that Meta-DREAM consistently outperforms existing state-of-the-art methods and verifies the effectiveness of each module.

With the recent improvement of deep learning (DL) techniques and computer hardware capabilities, neural networks are widely used to monitor massive sensor data and detect earthquakes in them. This makes designing fast, accurate, and generalized DL models necessary for an active field of research for automatic seismic phase picking. A seismic phase picking network called MFFnet is proposed to fuse power spectral density (PSD), expert knowledge, spectrograms, recurrence plots (RPs), and Gramian angle fields. The network uses fast Fourier convolution (FFC) on 2-D representations to extract more interpretable features. Considering the high proportion of noisy signals in field applications, MFFnet uses focal loss (FL) as the loss function to improve network accuracy. Experimental results show that MFFnet achieves precision, recall, and accuracy with 0.96, 0.98, and 0.98, respectively, in seismic phase detection tasks. Shapley value is used to evaluate the relationship between features and network predictions. Compared with other DL networks, the feature extraction approach used in this letter is more explanatory and provides greater confidence in the results.

Rapid and accurate classification of earthquake (eq) events is a serious challenge in seismology and disaster mitigation. Problems, such as data imbalance, model interpretability, and model generalization, limit the application of artificial intelligence methods in this research area. This article introduces a real-time two-stage diffusion eq event classification (DiffEEC) model based on the diffusion probability model (DPM). DiffEEC uses a two-stage classification approach and combines DPM and knowledge distillation (KD) techniques. DiffEEC focuses on seismic phase-related features and source mechanism-related features by combining time-series features extracted by convolutional layers, DPM output, and InSAR data features to better extract core seismic data information and reduce reliance on manual feature design. DiffEEC uses focal loss to solve the data imbalance problem. Thus, DiffEEC can address data scarcity and imbalance, feature acquisition and selection, variability and complexity of seismic event processing, and model generalization through the mechanism. Experiments show that DiffEEC performs better in eq event classification (EC).

Rapid and accurate seismic source characterization significantly influences the performance of Earthquake Early Warning (EEW) systems. However, the complexity of the seismic source modeling and the error accumulation during continuous characterization make it difficult to accurately characterize various source parameters. Furthermore, current artificial intelligence methods focus on a single task, lacking inter-task fusion and guidance from specialized knowledge. In this study, we propose a novel Deep Learning (DL) algorithm (SeisParaNet) to estimate P-wave arrival time, source location, and magnitude simultaneously based on a multi-task framework. To exploit seismological knowledge and attenuate the strong inter-task dependencies, this study incorporates arrival time differences information into the analysis of source localization parameters by using the attention mechanism and incorporates source location features into estimating local magnitude (ML). In addition, SeisParaNet uses a probability-based Self-Attention mechanism (Prob-Attention) to extract temporal information from waveforms. Experimental results demonstrate that, following a limited number of trainings on the STanford EArthquake Dataset (STEAD), SeisParaNet exhibits the capability to capture complex seismic patterns and rapidly characterize seismic sources. Furthermore, the introduction of Prob-Attention reduces computational complexity by 67%, validating the potential of SeisParaNet in EEW applications.

The hybrid flow shop scheduling (HFS) model has significant practical applicability in fields, such as manufacturing, transportation, service, and communication. However, learning effects, refer to the phenomenon of processors spending less processing time with more familiar operations, which are common constraints in actual production while often ignored in HFS research despite their significant impact on processing efficiency. In this article, an HFS problem with learning effects and release dates is investigated from a practical application perspective. For large-scale instances, a dispatching rule-based heuristic is developed with theoretical performance guarantees by demonstrating the asymptotic optimality and the tight worst-case bound. For small-scale instances, a branch-and-boun3d algorithm is designed to obtain an exact solution. An elaborate branching scheme, an idle-time-based pruning rule, and a task-splitting-based lower bound effectively reduce the search space. For medium-scale instances, a hybrid shuffled frog-leaping algorithm combined with macro evolution and local intensification is presented to search for high-quality solutions. Extensive experiments demonstrate the superiority of the developed algorithms against the state-of-the-art algorithms.

Peak ground acceleration (PGA) is a critical parameter in the postearthquake intensity snapshot. In this article, we propose a Bagged Tree for Rapid PGA Prediction (BTRPP) based on velocity waveforms recorded at stations around the epicenter, as well as a feature pruning algorithm based on BTRPP to predict PGA and analyze the relationship between PGA and manually predefined features. The research not only aims to discover the best model for forecasting PGA but also examines the impact of features using the interpretability of some models. As inputs to the model, BTRPP uses and mixes features in the time and frequency domains. Bayesian optimization (BO) is used to find the optimum hyperparameters of BTRPP. The results demonstrate that, using the data within 5 s after the first arrival of the P-wave, the BTRPP with BO can reduce the RMSE to 0.2076 and enhance the R-square to 0.91. It is, finally, found that the PGA is most closely related to the average positive amplitude, average negative amplitude, and spectral slope through the feature pruning algorithm in this article, which indicates that the results are plausible.

Abstract Community detection is one of the most popular researches in a variety of complex systems, ranging from biology to sociology. In recent years, there’s an increasing focus on the rapid development of more complicated networks, namely multilayer networks. Communities in a single-layer network are groups of nodes that are more strongly connected among themselves than the others, while in multilayer networks, a group of well-connected nodes are shared in multiple layers. Most traditional algorithms can rarely perform well on a multilayer network without modifications. Thus, in this paper, we offer overall comparisons of existing works and analyze several representative algorithms, providing a comprehensive understanding of community detection methods in multilayer networks. The comparison results indicate that the promoting of algorithm efficiency and the extending for general multilayer networks are also expected in the forthcoming studies.