152 citations · 231 across the 12 of their papers we have counts for
12 papers
Gaussian Process Limit Reveals Structural Benefits of Graph Transformers
Nil Ayday, Lingchu Yang, Debarghya Ghoshdastidar
Graph transformers are the state-of-the-art for learning from graph-structured data and are empirically known to avoid several pitfalls of message-passing architectures. However, t…
Retrieval-Augmented Diffusion Models for Time Series Forecasting
Jingwei Liu, Ling Yang, Hongyan Li +1
While time series diffusion models have received considerable focus from many recent works, the performance of existing models remains highly unstable. Factors limiting time series…
VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
Ling Yang, Ye Tian, Minkai Xu +7
GNN-to-MLP distillation aims to utilize knowledge distillation (KD) to learn computationally-efficient multi-layer perceptron (student MLP) on graph data by mimicking the output re…
Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization
Ling Yang, Jiayi Zheng, Heyuan Wang +5
Out-of-distribution (OOD) graph generalization are critical for many real-world applications. Existing methods neglect to discard spurious or noisy features of inputs, which are ir…
Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training
Ling Yang, Zhilin Huang, Yang Song +6
Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and the…
Diffusion Models: A Comprehensive Survey of Methods and Applications
Ling Yang, Zhilong Zhang, Yang Song +6
Diffusion models have emerged as a powerful new family of deep generative models with record-breaking performance in many applications, including image synthesis, video generation,…
Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning
Ling Yang, Shenda Hong
Unsupervised/self-supervised graph representation learning is critical for downstream node- and graph-level classification tasks. Global structure of graphs helps discriminating re…
Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer
Wenrui Zhang, Ling Yang, Shijia Geng +1
Unsupervised/self-supervised representation learning in time series is critical since labeled samples are usually scarce in real-world scenarios. Existing approaches mainly leverag…
Spatial Autoregressive Coding for Graph Neural Recommendation
Jiayi Zheng, Ling Yang, Heyuan Wang +4
Graph embedding methods including traditional shallow models and deep Graph Neural Networks (GNNs) have led to promising applications in recommendation. Nevertheless, shallow model…
Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion
Ling Yang, Shenda Hong
Unsupervised/self-supervised time series representation learning is a challenging problem because of its complex dynamics and sparse annotations. Existing works mainly adopt the fr…
Spectral Propagation Graph Network for Few-shot Time Series Classification
Ling Yang, Shenda Hong, Luxia Zhang
Few-shot Time Series Classification (few-shot TSC) is a challenging problem in time series analysis. It is more difficult to classify when time series of the same class are not com…
DPGN: Distribution Propagation Graph Network for Few-shot Learning
Ling Yang, Liangliang Li, Zilun Zhang +3
Most graph-network-based meta-learning approaches model instance-level relation of examples. We extend this idea further to explicitly model the distribution-level relation of one…