Robust heterogeneous network representation learning by multifaceted curriculum training.

Structural-aware key node identification in hypergraphs via representation learning and fine-tuning

Anomaly detection using case-based reasoning and representation learning: Application to industrial maintenance

Harnessing structure-aware graph representation and adaptive anchor graph learning for multi-view clustering

Graph Neural Networks (GNNs) have made significant strides in the analysis and modeling of complex network data, particularly excelling in graph and node classification tasks. However, the "closed box" nature of GNNs impedes user understanding and trust, thereby restricting their broader application. This challenge has spurred a growing focus on demystifying GNNs to make their decision-making processes more transparent. Traditional methods for explaining GNNs often rely on selecting subgraphs and employing combinatorial optimization to generate understandable outputs. However, these methods are closely linked to the inherent complexity of GNNs, leading to higher explanation costs. To address this issue, we introduce a lower-complexity proxy model to explain GNNs. Our approach leverages knowledge distillation with inter-layer alignment, specifically targeting the challenge of over-smoothing and its detrimental impact on model explanation. Initially, we distill critical insights from complex GNN models into a more manageable proxy model. We then apply an inter-layer alignment-based distillation technique to ensure alignment between the proxy and the original model, facilitating the extraction of node or edge-level explanations within the proxy framework. We theoretically prove that the explanations derived from the proxy model are faithful to both the proxy and the original model. Additionally, we show that the upper bound of unfaithfulness between the proxy and the original model remains consistent when the distillation error is infinitesimal. This inter-layer alignment knowledge distillation technique enables the proxy model to retain the knowledge learning and topological representation capabilities of the original model to the greatest extent. Experimental evaluations on numerous real-world datasets confirm the effectiveness of our method, demonstrating robust performance.

Disentangled molecular representation learning with context-aware codebook for OOD generalization

Hierarchical prototype-guided representation learning for robust graph classification

The rapid advancement of foundation models has revolutionized visual representation learning in a self-supervised manner. However, their application in remote sensing (RS) remains constrained by a fundamental gap: existing models predominantly handle single or limited modalities, overlooking the inherently multi-modal nature of RS observations. Optical, synthetic aperture radar (SAR), and multi-spectral data offer complementary insights that significantly reduce the inherent ambiguity and uncertainty in single-source analysis. To bridge this gap, we introduce RingMoE, a unified multi-modal RS foundation model with 14.7 billion parameters, pre-trained on 400 million multi-modal RS images from nine satellites. RingMoE incorporates three key innovations: 1) A hierarchical Mixture-of-Experts (MoE) architecture comprising modal-specialized, collaborative, and shared experts, effectively modeling intra-modal knowledge while capturing cross-modal dependencies to mitigate conflicts between modal representations; 2) Physics-informed self-supervised learning, explicitly embedding sensor-specific radiometric characteristics into the pre-training objectives; 3) Dynamic expert pruning, enabling adaptive model compression from 14.7B to 1B parameters while maintaining performance, facilitating efficient deployment in Earth observation applications. Evaluated across 23 benchmarks spanning six key RS tasks (i.e., classification, detection, segmentation, tracking, change detection, and depth estimation), RingMoE outperforms existing foundation models and sets new SOTAs, demonstrating remarkable adaptability from single-modal to multi-modal scenarios. Beyond theoretical progress, it has been deployed and trialed in multiple sectors, including emergency response, land management, marine sciences, and urban planning.

Multi-view feature representation learning: Integrating medical team information to enhance online physician recommendation

Citation importance-aware document representation learning for large-scale science mapping

DFSA-Net: an effective single image dehazing framework via frequency-domain processing and multi-scale representation learning

MC-HSTA: A multi-source cross-domain hybrid spatio-temporal attention network for traffic flow prediction.

Decoupling representation learning and classifier for long-tailed adversarial training

EEG-based epileptic seizure prediction with patient-tailored spectral-spatial-temporal feature learning.

CNER-Omni: A unified dynamic modality learning framework for Chinese named entity recognition across text and speech.

GraphProbe: Knowledge Probing for Graph Representation Learning

Granger-TSllm: Granger causality enhanced LLMs with residual-quantized tokenizer for multivariate time series forecasting.

Adaptive semi-supervised graph contrastive representation learning for robust emotion recognition using electroencephalogram

Multiple object stitching for unsupervised representation learning

HASNN: Hierarchical attention spiking neural network for dynamic graph representation learning