Multivariate time series forecasting (MTSF) aims to predict future values based on historical observations. Recently, Fuzzy Cognitive Maps (FCM) have emerged as a promising and interpretable approach for MTSF. However, existing FCM-based models suffer from two main limitations. First, their feature extraction mechanisms fail to effectively represent raw time series data, limiting the ability to capture complex spatiotemporal dependencies. Second, the single-variable composite modeling strategy adopted by high-order FCMs (HFCM) neglects holistic inter-variable relationships across time, leading to inefficiencies and a linear increase in model parameters. To overcome these challenges, we propose a novel framework—Context-Aware Enhanced FCM (CAE-FCM)—for interpretable MTSF. To address the first limitation, CAE-FCM introduces two complementary feature extraction modules: the Adaptive Graph Convolution (AGC) module, which captures spatial dependencies through neighborhood-aware information aggregation, and the Global-Local Context-Aware Mamba (GLCAM) module, which models temporal dependencies via a state space model (SSM) that learns global and local temporal dynamics. For second limitation, CAE-FCM integrates the extracted spatial and temporal features into unified high-dimensional representations for FCM nodes, enabling efficient and expressive modeling of complex spatiotemporal interactions. Extensive experiments on five benchmark datasets demonstrate that CAE-FCM achieves state-of-the-art performance, significantly outperforming HFCM-based baselines in both forecasting accuracy and computational efficiency.

Most existing graph clustering methods primarily focus on exploiting topological structure, often neglecting the "missing-half" node feature information, especially how these features can enhance clustering performance. This issue is further compounded by the challenges associated with high-dimensional features. Feature selection in graph clustering is particularly difficult because it requires simultaneously discovering clusters and identifying the relevant features for these clusters. To address this gap, we introduce a novel paradigm called "one node one model", which builds an exclusive model for each node and defines the node label as a combination of predictions for node groups. Specifically, the proposed "Feature Personalized Graph Clustering (FPGC)" method identifies cluster-relevant features for each node using a squeeze-and-excitation block, integrating these features into each model to form the final representations. Additionally, the concept of feature cross is developed as a data augmentation technique to learn low-order feature interactions. Extensive experimental results demonstrate that FPGC outperforms state-of-the-art clustering methods. Moreover, the plug-and-play nature of our method provides a versatile solution to enhance GNN-based models from the feature perspective.

Few-shot counting (FSC) aims to train a generalized visual counting model that can count any novel category given a small number of support samples. Current prevalent approaches treat FSC as a feature-matching task, leveraging attention to aggregate information from all other query patches or supports for each query patch. However, we notice that this operation blends target features with non-target features, making it difficult for the model to differentiate between targets and non-targets, thereby impacting counting accuracy. To tackle this issue, we develop a Decoupled Feature Matching Module (DFMM), which decouples target and non-target regions and conducts self-aggregation within respective regions. Furthermore, we design a Consistency Alignment Loss (CAL) to facilitate discriminative ability between targets and non-targets across multiple scales. Besides, we adopt a localization paradigm for counting and propose an Anchor-based Assignment Strategy to stabilize the optimization process and improve counting accuracy. Experiments on FSC147 and CARPK demonstrate that our method can achieve performance on par with state-of-the-art methods. Qualitative and quantitative experiments both confirm the efficacy of our proposed components.

Multimodal graphs, which integrate unstructured heterogeneous data with structured interconnections, offer substantial real-world utility but remain insufficiently explored in unsupervised learning. In this work, we initiate the study of multimodal graph clustering, aiming to bridge this critical gap. Through empirical analysis, we observe that real-world multimodal graphs often exhibit hybrid neighborhood patterns, combining both homophilic and heterophilic relationships. To address this challenge, we propose a novel framework---Disentangled Multimodal Graph Clustering (DMGC) ---which decomposes the original hybrid graph into two complementary views: (1) a homophily-enhanced graph that captures cross-modal class consistency, and (2) heterophily-aware graphs that preserve modality-specific inter-class distinctions. We introduce a Multimodal Dual-frequency Fusion mechanism that jointly filters these disentangled graphs through a dual-pass strategy, enabling effective multimodal integration while mitigating category confusion. Our self-supervised alignment objectives further guide the learning process without requiring labels. Extensive experiments on both multimodal and multi-relational graph datasets demonstrate that DMGC achieves state-of-the-art performance, highlighting its effectiveness and generalizability across diverse settings. Our code is available at https://github.com/Uncnbb/DMGC.

In today's digital era driven by data, the amount and complexity of the collected data, such as multiview, non-Euclidean, and multirelational, are growing exponentially or even faster. Clustering, which unsupervisedly extracts valid knowledge from data, is extremely useful in practice. However, existing methods are independently developed to handle one particular challenge at the expense of the others. In this work, we propose a simple but effective framework for complex data clustering (CDC) that can efficiently process different types of data with linear complexity. We first use graph filtering (GF) to fuse geometric structure and attribute information. We then reduce complexity with high-quality anchors that are adaptively learned via a novel similarity-preserving (SP) regularizer. We illustrate the cluster-ability of our proposed method theoretically and experimentally. In particular, we deploy CDC to graph data of size 111 M.