Multivariate time-series analysis involves extracting informative representations from sequences of multiple interdependent variables, supporting tasks such as forecasting, imputation, and anomaly detection. In real-world scenarios, these variables are typically collected from a shared context or underlying phenomenon, suggesting the presence of latent dependencies across time and channels that can be leveraged to improve performance. However, recent findings show that channel-independent (CI) models, which assume no inter-variable dependencies, often outperform channel-dependent (CD) models that explicitly model such relationships. This surprising result indicates that current CD models may not fully exploit their potential due to limitations in how dependencies are captured. Recent studies have revisited channel dependence modeling with various approaches; however, these methods often employ indirect modeling strategies, which can lead to meaningful dependencies being overlooked. To address this issue, we introduce XCTFormer, a transformer-based channel-dependent (CD) model that explicitly captures cross-temporal and cross-channel dependencies via an enhanced attention mechanism. The model operates in a token-to-token fashion, modeling pairwise dependencies between every pair of tokens across time and channels. The architecture comprises (i) a data processing module, (ii) a novel Cross-Relational Attention Block (CRAB) that increases capacity and expressiveness, and (iii) an optional Dependency Compression Plugin (DeCoP) that improves scalability. Through extensive experiments on three time-series benchmarks, we show that XCTFormer achieves strong results compared to widely recognized baselines; in particular, it attains state-of-the-art performance on the imputation task, outperforming the second-best method by an average of 20.8% in MSE and 15.3% in MAE.
Multi-Window Temporal Analysis for Enhanced Arrhythmia Classification: Leveraging Long-Range Dependencies in Electrocardiogram Signals
AI4Health Department, Oldenburg University(奥尔登堡大学AI4Health部门);Department of Cardiology, Angiology and Intensive Care Medicine, Charité Campus Mitte, German Heart Center of the Charité-University Medicine Berlin(查理医院梅特校区心内科、血管科和重症医学科,查理-柏林大学医学中心心脏中心)
Leveraging Time-Series Foundation Model for Subsurface Well Logs Prediction and Anomaly Detection
King Fahd University of Petroleum and Minerals(法赫德石油和矿产大学);Center for Integrative Petroleum Research(综合石油研究中心);College of Petroleum Engineering and Geosciences(石油工程与地球科学学院)
Accurate and Robust Generative Approach for Overcoming Data Sparsity and Imbalance in Landslide Modeling with A Tabular Foundation Model
School of Engineering and Technology, China University of Geosciences (Beijing)(工程与技术学院,中国地质大学(北京));School of Geological Engineering and Geomatics, Chang'an University(地质工程与测绘学院,长安大学)
Infinite-Horizon Graph Filters: Leveraging Power Series to Enhance Sparse Information Aggregation
Key Laboratory of High Confidence Software Technologies (Peking University)(北京大学高可信软件技术重点实验室);University of Toronto(多伦多大学);Ministry of Education(教育部);School of Computer Science, Peking University(北京大学计算机学院);Big Data Technology Research Center, Nanhu Laboratory(南湖实验室大数据技术研究中心)