Pre-trained models have demonstrated exceptional generalization capabilities in time-series forecasting; however, adapting them to evolving data distributions remains a significant challenge. A key hurdle lies in accessing the original training data, as fine-tuning solely on new data often leads to catastrophic forgetting. To address this issue, we propose Replay Tuning (R-Tuning), a novel framework designed for the continual adaptation of pre-trained time-series models. R-Tuning constructs a unified latent space that captures both prior and current task knowledge through a frequency-aware replay strategy. Specifically, it augments model-generated samples via wavelet-based decomposition across multiple frequency bands, generating trend-preserving and fusion-enhanced variants to improve representation diversity and replay efficiency. To further reduce reliance on synthetic samples, R-Tuning introduces a latent consistency constraint that aligns new representations with the prior task space. This constraint guides joint optimization within a compact and semantically coherent latent space, ensuring robust knowledge retention and adaptation. Extensive experimental results demonstrate the superiority of R-Tuning, which reduces MAE and MSE by up to 46.9% and 46.8%, respectively, on new tasks, while preserving prior knowledge with gains of up to 5.7% and 6.0% on old tasks. Notably, under few-shot settings, R-Tuning outperforms all state-of-the-art baselines even when synthetic proxy samples account for only 5% of the new task dataset.

Encoding time series into tokens and using language models for processing has been shown to substantially augment the models' ability to generalize to unseen tasks. However, existing language models for time series forecasting encounter several obstacles, including aliasing distortion and prolonged inference times, primarily due to the limitations of quantization processes and the computational demands of large models. This paper introduces Apollo-Forecast, a novel framework that tackles these challenges with two key innovations: the Anti-Aliasing Quantization Module (AAQM) and the Race Decoding (RD) technique. AAQM adeptly encodes sequences into tokens while mitigating high-frequency noise in the original signals, thus enhancing both signal fidelity and overall quantization efficiency. RD employs a draft model to enable parallel processing and results integration, which markedly accelerates the inference speed for long-term predictions, particularly in large-scale models. Extensive experiments on various real-world datasets show that Apollo-Forecast outperforms state-of-the-art methods by 35.41% and 18.99% in WQL and MASE metrics, respectively, in zero-shot scenarios. Furthermore, our method achieves an acceleration of 1.9X-2.7X in inference speed over the baseline methods.

Language models have been proven to handle time series data after tokenization and show generalization performance on unseen forecasting tasks. However, existing techniques for tokenizing time series data struggle to eliminate redundant information and noise, which can lead to signal aliasing and cumulative quantization errors, making it difficult to further improve prediction performance. In this paper, we propose an Adaptive Component Extraction and Tokenization (ACET) framework, which includes two key novelties to address these challenges: the Dynamic Component Extraction Module (DCEM) and the Time Series Tokenization Module (TSTM). The DCEM dynamically isolates the principal components from the interference in the original signal, eliminating the need for manual parameter tuning. This not only enhances the accuracy of signal tokenization but also mitigates the adverse effects of high-frequency noise. Then, the TSTM tokenizes continuous time series data while preserving long-term trend features, ensuring that critical information is retained for subsequent forecasting. Extensive cross-domain experiments on various real-world datasets demonstrate that, in zero-shot forecasting scenarios, ACET achieves improvements of 19.27% in WQL and 6.63% in MASE, compared to baseline methods.

Optimizing resource allocation is critical to achieving energy-efficient industrial Internet-of-Things (IIoT). Many tasks that require grouping IIoT devices with rich connectivity can be modeled as the well-known graph partitioning problem. However, little attention has been paid to those tasks where nodes with few connections are expected to be clustered together, which is the inverse graph partitioning (IGP) problem. Here, we focus on the IGP problem abstracted from real IIoT applications, such as spectrum allocation. First, we build a unified mathematical model for the IGP problem and analyze its characteristics in detail. Then, a novel optimization approach is proposed to provide compelling solutions, which incorporates a node clustering model based on a graph convolutional network (GCN) and a node swap procedure for local optimization. We compare the proposed approach with various baselines on substantial synthetic and real-world networks. Empirical results show that the proposed approach achieves excellent performance, especially in large networks.

Simpson's paradox is a well-known statistical phenomenon that has captured the attention of statisticians, mathematicians, and philosophers for more than a century. The paradox often confuses people when it appears in data, and ignoring it may lead to incorrect decisions. Recent studies have found many examples of Simpson's paradox in social data and proposed a few methods to detect the paradox automatically. However, these methods suffer from many limitations, such as being only suitable for categorical variables or one specific paradox. To address these problems, we develop a learning-based approach to discover various Simpson's paradoxes. Firstly, we propose a framework from a statistical perspective that unifies multiple variants of Simpson's paradox currently known. Secondly, we present a novel loss function, Multi-group Pearson Correlation Coefficient (MPCC), to calculate the association strength of two variables of multiple subgroups. Then, we design a neural network model, coined SimNet, to automatically disaggregate data into multiple subgroups by optimizing the MPCC loss. Experiments on various datasets demonstrate that SimNet can discover various Simpson's paradoxes caused by discrete and continuous variables, even hidden variables. The code is available at https://github.com/ant-research/Learning-to-Discover-Various-Simpson-Paradoxes.

Mechanical fault diagnosis is crucial to ensure the safe operations of equipment in intelligent manufacturing systems. Deep learning-based methods have been recently developed for fault diagnosis due to their advantages in feature representation. However, most of these methods fail to learn relations between samples and thus perform poorly without sufficient labeled data. In this article, we propose a new few-shot learning method named dual graph neural network (DGNNet) with residual blocks to address fault diagnosis problems with limited data. First, the residual module learns the feature of samples with image data transferred from original signals. Second, two complete graphs built on the sample features are used to extract the instance-level and distribution-level relations between samples. In particular, an alternate update policy between the instance and distribution graphs integrates the multilevel relations to propagate the label information of a few labeled samples to unlabeled samples. This technique leverages labeled and unlabeled samples to identify unseen faults, encouraging DGNNet competency in fault diagnosis tasks with very few labeled samples. Extensive results on various datasets show that DGNNet achieves excellent performance in supervised fault diagnosis tasks and outperforms baselines by a great margin in semisupervised cases.

Link prediction plays an important role in complex network analysis. It is to predict the existence of an unknown link or a future link in a network. Classical methods for link prediction evaluate the similarity of vertices based on common neighbors, and denote that every common neighbor makes equal contribution to the connection likelihood. However, common neighbors may play different roles depending on whether they belong to the same community, where vertices are densely or sparsely connected to other communities. This paper proposes a novel similarity index for link prediction which combines the topology information and community information. The proposed approach is compared with ten classical local similarity indices on ten real-world networks. The experiment results shown that the proposed approach can improve the accuracy of link prediction no matter which community detection algorithm is used.