Accurate time series forecasting is essential for proactive management and resource allocation in intelligent IoT systems, where data are often affected by sensor noise, multi-scale periodicity, and cross-frequency interactions. Although decomposition-based frameworks are widely adopted, most existing approaches rely on time-domain modeling with limited nonlinear capacity or treat frequency decomposition as a generic preprocessing step. Such designs fail to align model inductive bias with the intrinsic multi-scale structure of seasonal dynamics, leading to incomplete seasonal representations and degraded forecasting performance. To address this limitation, we propose Detail-aware Wavelet Decomposition and Mixing (DWDMixer), a seasonal-centric forecasting architecture built on multi-scale representation learning and seasonal-trend decomposition, where trend components serve as complementary signals. To enable fine-grained seasonal modeling, we propose a Detail-aware Wavelet Transform Hybrid (DWTH) block that performs hierarchical wavelet decomposition guided by detail-sensitive representations. DWTH captures cross-scale and cross-frequency interactions while jointly modeling temporal and spectral information, yielding expressive multi-resolution representations. Extensive experiments on 10 benchmark datasets demonstrate that DWDMixer significantly outperforms state-of-the-art models, achieving error reductions of up to 9% in MSE for long-term forecasting and 22% in MAE for short-term forecasting. Our code is available at https://github.com/zpc2002zpc/DWDMixer.

Open intent classification is critical for the development of dialogue systems, aiming to accurately classify known intents into their corresponding classes while identifying unknown intents. Prior boundary-based methods assumed known intents fit within compact spherical regions, focusing on coarse-grained representation and precise spherical decision boundaries. However, these assumptions are often violated in practical scenarios, making it difficult to distinguish known intent classes from unknowns using a single spherical boundary. To tackle these issues, we propose a Multi-granularity Open intent classification method via adaptive Granular-Ball decision boundary (MOGB). Our MOGB method consists of two modules: representation learning and decision boundary acquiring. To effectively represent the intent distribution, we design a hierarchical representation learning method. This involves iteratively alternating between adaptive granular-ball clustering and nearest sub-centroid classification to capture fine-grained semantic structures within known intent classes. Furthermore, multi-granularity decision boundaries are constructed for open intent classification by employing granular-balls with varying centroids and radii. Extensive experiments conducted on three public datasets demonstrate the effectiveness of our proposed method.

As the spatio-temporal data of a city is not always available, insufficient data would lead to poor performance in some urban prediction tasks. Existing works utilize transfer learning to solve the data scarcity problem, but they ignore the differences in data distributions across cities, which leads to the ineffectiveness of knowledge transfer. In this paper, we propose a domain adversarial model with knowledge transfer for spatio-temporal prediction across cities, entitledCityTrans. Specifically, 1) the self-adaptive spatio-temporal knowledge (namely ST-Knowledge) is mined, to learn the latent spatial and temporal patterns among cities; 2) the domain-adversarial training strategy is introduced to enhance domain invariance; 3) a knowledge attention mechanism is proposed to extract the transferable information from the ST-Knowledge. Note that our CityTrans is an end-to-end domain adversarial spatio-temporal network without two-stage training (i.e., pre-training and fine-tuning). Finally, we conduct extensive experiments on two spatio-temporal prediction tasks: traffic (flow and speed) prediction, and air quality prediction. Experimental results demonstrate that CityTrans outperforms state-of-the-art models on all tasks by a significant margin.

Traffic prediction is the cornerstone of the intelligent transportation system (ITS), and accurate prediction is essential for planning route, alleviating traffic pressure, and optimizing public transportation resource allocation. Although many methods have been proposed, they still have deficiencies in capturing the spatial-temporal dependence of traffic data. In specific, their network structures are usually discrete, making it is challenging to continuously model the dynamic spatial-temporal patterns of the road network. Besides, static graph structure of the road network is not sufficient to express dynamic traffic patterns. In this paper, we propose a diffusion graph neural ordinary differential equation network (DGODE) to address the above challenges for traffic prediction. Firstly, DGODE represents the node relationships of the road network as a bidirectional spatial graph and the node relationships of the time as a unidirectional temporal graph, and then generates an adaptive diffusion matrix to explore potential node relationships and capture spatial and temporal dependencies. Next, the neural ordinary differential equation (NODE) is introduced to contin-uously model the dynamical change of traffic network, making it possible to capture global dependence at a deeper network structure. Since the solution of the ordinary differential equation is determined by the initial state, we design the structure with a jump link to supplement the spatial-temporal information in the historical data. Finally, the experimental evaluation on four real-world datasets shows that DGODE is significantly superior to several baseline methods.

Air quality prediction has received widespread attention from both the governments and citizens due to its close relation to our lives. Analyzing the spatial relations and temporal trends in air quality data is essential for air quality prediction task. However, most existing approaches require a pre-defined graph structure to capture the spatial dependencies of air quality data, and thus they can not be applied when a well-defined graph structure is unavailable. Besides, those methods do not give sufficient consideration to the latent relationships among entities of the graph over time. To overcome the above limitations, we propose a Spatial-Temporal Dynamic Graph Convolution Neural Network (ST-DGCN) in this paper. Our approach develops a dynamic adjacency matrix into graph convolution layer, which extracts the potential and time-varying spatial dependencies. To jointly model the spatial and temporal correlations, we combine dynamic graph convolution with gated recurrent unit and propose a unified DGC-GRU block. Next, a residual operation is further introduced into the DGC-GRU to simultaneously handle the information from different particles. Experimental results demonstrate that the proposed method outperforms the state-of-art baselines on two real-world air quality datasets.