444 citations · 497 across the 49 of their papers we have counts for
24 papers · 1 filter
Learning Spatio-Temporal Foundation Models from Pure Synthetic Data
Yutong Feng, Shiyuan Piao, Yutong Xia +5
Spatio-Temporal Foundation Models (STFMs) aim to learn generalizable representations of complex dynamical systems across space and time. However, existing approaches suffer from di…
Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps
Jiashun Cheng, Aochuan Chen, Nuo Chen +4
Low-Rank Adaptation (LoRA) has emerged as a prominent technique for fine-tuning large foundation models. Despite its successes, the substantial parameter redundancy, which limits t…
Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection
Yunhui Liu, Jiashun Cheng, Yiqing Lin +7
Graph anomaly detection (GAD) has garnered increasing attention in recent years, yet remains challenging due to two key factors: (1) label scarcity stemming from the high cost of a…
MedSpaformer: a Transferable Transformer with Multi-granularity Token Sparsification for Medical Time Series Classification
Jiexia Ye, Weiqi Zhang, Ziyue Li +2
Accurate medical time series (MedTS) classification is essential for effective clinical diagnosis, yet remains challenging due to complex multi-channel temporal dependencies, infor…
CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer
Yang Liu, Zinan Zheng, Jiashun Cheng +4
Accurate Subseasonal-to-Seasonal (S2S) climate forecasting is pivotal for decision-making including agriculture planning and disaster preparedness but is known to be challenging du…
Heterophilic Graph Neural Networks Optimization with Causal Message-passing
Botao Wang, Jia Li, Heng Chang +2
In this work, we discover that causal inference provides a promising approach to capture heterophilic message-passing in Graph Neural Network (GNN). By leveraging cause-effect anal…
LeMoLE: LLM-Enhanced Mixture of Linear Experts for Time Series Forecasting
Lingzheng Zhang, Lifeng Shen, Yimin Zheng +3
Recent research has shown that large language models (LLMs) can be effectively used for real-world time series forecasting due to their strong natural language understanding capabi…
Graph Pre-Training Models Are Strong Anomaly Detectors
Jiashun Cheng, Zinan Zheng, Yang Liu +5
Graph Anomaly Detection (GAD) is a challenging and practical research topic where Graph Neural Networks (GNNs) have recently shown promising results. The effectiveness of existing…
Toward Physics-guided Time Series Embedding
Jiaxi Hu, Bowen Zhang, Qingsong Wen +2
In various scientific and engineering fields, the primary research areas have revolved around physics-based dynamical systems modeling and data-driven time series analysis. Accordi…
Disentangling Likes and Dislikes in Personalized Generative Explainable Recommendation
Ryotaro Shimizu, Takashi Wada, Yu Wang +9
Recent research on explainable recommendation generally frames the task as a standard text generation problem, and evaluates models simply based on the textual similarity between t…
Enabling Tensor Decomposition for Time-Series Classification via A Simple Pseudo-Laplacian Contrast
Man Li, Ziyue Li, Lijun Sun +1
Tensor decomposition has emerged as a prominent technique to learn low-dimensional representation under the supervision of reconstruction error, primarily benefiting data inference…
MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning
Jiexia Ye, Weiqi Zhang, Ziyue Li +3
The recent rapid advancements in language models (LMs) have garnered attention in medical time series-text multimodal learning. However, existing contrastive learning-based and pro…
Empowering Time Series Analysis with Foundation Models: A Comprehensive Survey
Jiexia Ye, Yongzi Yu, Weiqi Zhang +3
Time series data are ubiquitous across diverse real-world applications, making time series analysis critically important. Traditional approaches are largely task-specific, offering…
Deep Insights into Noisy Pseudo Labeling on Graph Data
Botao Wang, Jia Li, Yang Liu +4
Pseudo labeling (PL) is a wide-applied strategy to enlarge the labeled dataset by self-annotating the potential samples during the training process. Several works have shown that i…
MFRL-BI: Design of a Model-free Reinforcement Learning Process Control Scheme by Using Bayesian Inference
Yanrong Li, Juan Du, Wei Jiang
Design of process control scheme is critical for quality assurance to reduce variations in manufacturing systems. Taking semiconductor manufacturing as an example, extensive litera…
A Co-training Approach for Noisy Time Series Learning
Weiqi Zhang, Jianfeng Zhang, Jia Li +1
In this work, we focus on robust time series representation learning. Our assumption is that real-world time series is noisy and complementary information from different views of t…
SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases
Yang Liu, Jiashun Cheng, Haihong Zhao +5
Graph Neural Networks (GNNs) with equivariant properties have emerged as powerful tools for modeling complex dynamics of multi-object physical systems. However, their generalizatio…
Correlated Time Series Self-Supervised Representation Learning via Spatiotemporal Bootstrapping
Luxuan Wang, Lei Bai, Ziyue Li +2
Correlated time series analysis plays an important role in many real-world industries. Learning an efficient representation of this large-scale data for further downstream tasks is…
Data Imputation from the Perspective of Graph Dirichlet Energy
Weiqi Zhang, Guanlue Li, Jianheng Tang +2
Data imputation is a crucial task due to the widespread occurrence of missing data. Many methods adopt a two-step approach: initially crafting a preliminary imputation (the "draft"…
Human Mobility Modeling During the COVID-19 Pandemic via Deep Graph Diffusion Infomax
Yang Liu, Yu Rong, Zhuoning Guo +4
Non-Pharmaceutical Interventions (NPIs), such as social gathering restrictions, have shown effectiveness to slow the transmission of COVID-19 by reducing the contact of people. To…
Handling Missing Data via Max-Entropy Regularized Graph Autoencoder
Ziqi Gao, Yifan Niu, Jiashun Cheng +6
Graph neural networks (GNNs) are popular weapons for modeling relational data. Existing GNNs are not specified for attribute-incomplete graphs, making missing attribute imputation…
Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning
Jiashun Cheng, Man Li, Jia Li +1
Graph self-supervised learning (SSL) has been vastly employed to learn representations from unlabeled graphs. Existing methods can be roughly divided into predictive learning and c…
Long-Short Term Spatiotemporal Tensor Prediction for Passenger Flow Profile
Ziyue Li, Hao Yan, Chen Zhang +1
Spatiotemporal data is very common in many applications, such as manufacturing systems and transportation systems. It is typically difficult to be accurately predicted given intrin…
Tensor Completion for Weakly-dependent Data on Graph for Metro Passenger Flow Prediction
Ziyue Li, Nurettin Dorukhan Sergin, Hao Yan +2
Low-rank tensor decomposition and completion have attracted significant interest from academia given the ubiquity of tensor data. However, the low-rank structure is a global proper…