Explanipedia

Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning Open

Yang Li, Aming Wu, Zihao Zhang, Yahong Han · 2025

In this paper, we focus on Novel Class Discovery for Point Cloud Segmentation (3D-NCD), aiming to learn a model that can segment unlabeled (novel) 3D classes using only the supervision from labeled (base) 3D classes. The key to this task i…

Human knowledge-enhanced large language model agent for prediction of intestinal disease progression in patients with Crohn’s disease: A multicenter retrospective study Open

Zhoulei Li, Fangping He, Ruonan Zhang, Shanshan Zhu, Qinxian Chen , et al. · 2025

Causal-aware Graph Neural Architecture Search under Distribution Shifts Open

Peiwen Li, Xin Wang, Zeyang Zhang, Ziwei Zhang, Fang Shen , et al. · 2025

Understanding Knowledge Transferability for Transfer Learning: A Survey Open

Haoxiang Wang, Jingge Wang, Zhihui Zhao, Yang Tan, Yanru Wu , et al. · 2025

Transfer learning has become an essential paradigm in artificial intelligence, enabling the transfer of knowledge from a source task to improve performance on a target task. This approach, particularly through techniques such as pretrainin…

Reinforced Domain Selection for Continuous Domain Adaptation Open

Hanbing Liu, Huaze Tang, Yanru Wu, Yang Li, Xiao–Ping Zhang · 2025

Continuous Domain Adaptation (CDA) effectively bridges significant domain shifts by progressively adapting from the source domain through intermediate domains to the target domain. However, selecting intermediate domains without explicit m…

Exploiting Task Relationships for Continual Learning Using Transferability-Aware Task Embeddings Open

Yanru Wu, Xiangyu Chen, Jianning Wang, Enming Zhang, Hanbing Liu , et al. · 2025

Continual learning (CL) has been a critical topic in contemporary deep neural network applications, where higher levels of both forward and backward transfer are desirable for an effective CL performance. Existing CL strategies primarily f…

Non-destructive degradation pattern decoupling for early battery trajectory prediction <i>via</i> physics-informed learning Open

Shengyu Tao, Mengtian Zhang, Zixi Zhao, Haoyang Li, Ruifei Ma , et al. · 2025

The paper proposes a physics-informed model to predict battery lifetime trajectories by computing thermodynamic and kinetic parameters, saving costly data that has not been established for sustainable manufacturing, reuse, and recycling.

Predicting community case transfer path and processing time using decoder models Open

Yiwen Liu, Dongdong Zhang, Xinyu Yang, Yuanbo Tang, Yang Chen , et al. · 2024

Generative learning assisted state-of-health estimation for sustainable battery recycling with random retirement conditions Open

Shengyu Tao, Ruifei Ma, Zixi Zhao, Gengyu Ma, Lin Su , et al. · 2024

RealTCD: Temporal Causal Discovery from Interventional Data with Large Language Model Open

Peiwen Li, Xin Wang, Zeyang Zhang, Yuan Meng, Fang Shen , et al. · 2024

Estimating and modeling spontaneous mobility changes during the COVID-19 pandemic without stay-at-home orders Open

Baining Zhao, Xuzhe Wang, Tianyu Zhang, Rongye Shi, Fengli Xu , et al. · 2024

Comprehending the complex interplay among urban mobility, human behavior, and the COVID-19 pandemic could deliver vital perspectives to steer forthcoming public health endeavors. In late 2022, China lifted its "Zero-COVID" policy and rapid…

A Geometric Algorithm for Blood Vessel Reconstruction from Skeletal Representation Open

Guoqing Zhang, Yang Li · 2024

CareerMiner: Automatic extraction of professional network from large Chinese resume data Open

Qiqi Chen, Dexu Kong, Yongchi Zhu, Zitao Shen, Chengyue Lu , et al. · 2023

The professional contacts of a person, including their past colleagues and supervisors, can play an important role in job recommendation and intelligent human resources management. However, collecting such information on a large scale can …

Explainable Trajectory Representation through Dictionary Learning Open

Yuanbo Tang, Zhiyuan Peng, Yang Li · 2023

Trajectory representation learning on a network enhances our understanding of vehicular traffic patterns and benefits numerous downstream applications. Existing approaches using classic machine learning or deep learning embed trajectories …

Identification of Influencing Factors on Self-reported Count Data with Multiple Potential Inflated Values Open

Yang Li, Mingcong Wu, Mengyun Wu, Shuangge Ma · 2023

The Online Chauffeured Service Demand (OCSD) research is an exploratory market study of designated driver services in China. Researchers are interested in the influencing factors of chauffeured service adoption and usage and have collected…

InferTurbo: A Scalable System for Boosting Full-graph Inference of Graph Neural Network over Huge Graphs Open

Dalong Zhang, Xianzheng Song, Zhiyang Hu, Yang Li, Tao Miao , et al. · 2023

GNN inference is a non-trivial task, especially in industrial scenarios with giant graphs, given three main challenges, i.e., scalability tailored for full-graph inference on huge graphs, inconsistency caused by stochastic acceleration str…

The safety and efficacy of left atrial BOX ablation in persistent atrial fibrillation：A meta-analysis Open

Xi Yin, Yang Li, Wenyu Zhang, Jie Hao · 2023

Background: Catheter ablation is an effective method to control the rhythm of atrial fibrillation. Circumferential pulmonary vein isolation (CPVI) is the cornerstone of catheter ablation of atrial fibrillation.However, circumferential pulm…

Learn from Yesterday: A Semi-supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streams Open

Yongrui Chen, Xinnan Guo, Tongtong Wu, Guilin Qi, Yang Li , et al. · 2023

Conventional text-to-SQL studies are limited to a single task with a fixed-size training and test set. When confronted with a stream of tasks common in real-world applications, existing methods struggle with the problems of insufficient su…

SDG-L: A Semiparametric Deep Gaussian Process based Framework for Battery Capacity Prediction Open

Hanbing Liu, Yanru Wu, Yang Li, Erçan E. Kuruoğlu, Xuan Zhang · 2023

Lithium-ion batteries are becoming increasingly omnipresent in energy supply. However, the durability of energy storage using lithium-ion batteries is threatened by their dropping capacity with the growing number of charging/discharging cy…

NRTSI: Non-Recurrent Time Series Imputation Open

Siyuan Shan, Yang Li, Junier B. Oliva · 2023

Time series imputation is a fundamental task for understanding time series with missing data. Existing methods either do not directly handle irregularly-sampled data or degrade severely with sparsely observed data. In this work, we reformu…

Multi-Task Sub-Band Network For Deep Residual Echo Suppression Open

Jiayao Sun, Dawei Luo, Zhaoxia Li, Jindong Li, Yukai Ju , et al. · 2023

This paper introduces the SWANT team entry to the ICASSP 2023 AEC Challenge. We submit a system that cascades a linear filter with a neural post-filter. Particularly, we adopt sub-band processing to handle full-band signals and shape the n…

Battery Cross-Operation-Condition Lifetime Prediction via Interpretable Feature Engineering Assisted Adaptive Machine Learning Open

Shengyu Tao, Chongbo Sun, Shiyi Fu, Yu Wang, Zhiyuan Han , et al. · 2023

An Information-Theoretic Approach to Transferability in Task Transfer Learning Open

Yajie Bao, Yang Li, Shao‐Lun Huang, Lin Zhang, Lizhong Zheng , et al. · 2022

Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks. An important question is to determine task transferability, i.e. given a common in…

Learn from Yesterday: A Semi-Supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streams Open

Yongrui Chen, Xinnan Guo, Tongtong Wu, Guilin Qi, Yang Li , et al. · 2022

Conventional text-to-SQL studies are limited to a single task with a fixed-size training and test set. When confronted with a stream of tasks common in real-world applications, existing methods struggle with the problems of insufficient su…

Transferability-Guided Cross-Domain Cross-Task Transfer Learning Open

Yang Tan, Yang Li, Shao‐Lun Huang, Xiao–Ping Zhang · 2022

We propose two novel transferability metrics F-OTCE (Fast Optimal Transport based Conditional Entropy) and JC-OTCE (Joint Correspondence OTCE) to evaluate how much the source model (task) can benefit the learning of the target task and to …

NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning Open

Wentao Zhang, Zeang Sheng, Mingyu Yang, Yang Li, Yu Shen , et al. · 2022

Recently, graph neural networks (GNNs) have shown prominent performance in graph representation learning by leveraging knowledge from both graph structure and node features. However, most of them have two major limitations. First, GNNs can…

DFG-NAS: Deep and Flexible Graph Neural Architecture Search Open

Wentao Zhang, Zheyu Lin, Yu Shen, Yang Li, Zhi Yang , et al. · 2022

Graph neural networks (GNNs) have been intensively applied to various graph-based applications. Despite their success, manually designing the well-behaved GNNs requires immense human expertise. And thus it is inefficient to discover the po…

Optimising self-organised volunteer efforts in response to the COVID-19 pandemic Open

Anping Zhang, Ke Zhang, Wanda Li, Yue Wang, Yang Li , et al. · 2022

Crowdsource volunteering efforts have contributed significantly to pandemic response and recovery during the COVID-19 outbreak. In such efforts, individual volunteers can collaborate to achieve rapid mobilisation toward emergent community …

Replication Data for: Optimising Self-Organised Volunteer Efforts in Response to the COVID-19 Pandemic Open

Anping Zhang, Ke Zhang, Wanda Li, Yue Wang, Yang Li , et al. · 2022

The attached file includes all data and code for the analysis.

Data Augmentation for Audio-Visual Emotion Recognition with an Efficient Multimodal Conditional GAN Open

Fei Ma, Yang Li, Shiguang Ni, Shao‐Lun Huang, Lin Zhang · 2022

Audio-visual emotion recognition is the research of identifying human emotional states by combining the audio modality and the visual modality simultaneously, which plays an important role in intelligent human-machine interactions. With th…

Yang Li YOU? Author Swipe