283 citations · 817 across the 58 of their papers we have counts for
36 papers · 1 filter
RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting
Hao-Nan Shi, Tong Wu, Chen-Cong Sun +3
Time-series foundation models (TSFMs) perform strongly across forecasting tasks, but their per-series inference is ill-suited to neighbor-rich forecasting, where each query has acc…
Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later
Han-Jia Ye, Huai-Hong Yin, De-Chuan Zhan +1
The widespread enthusiasm for deep learning has recently expanded into the domain of tabular data. Recognizing that the advancement in deep tabular methods is often inspired by cla…
A Closer Look at Deep Learning Methods on Tabular Datasets
Han-Jia Ye, Si-Yang Liu, Hao-Run Cai +2
Tabular data is prevalent across diverse domains in machine learning. With the rapid progress of deep tabular prediction methods, especially pretrained (foundation) models, there i…
Bridge the Modality and Capability Gaps in Vision-Language Model Selection
Chao Yi, Yu-Hang He, De-Chuan Zhan +1
Vision Language Models (VLMs) excel in zero-shot image classification by pairing images with textual category names. The expanding variety of Pre-Trained VLMs enhances the likeliho…
Continual Learning with Pre-Trained Models: A Survey
Da-Wei Zhou, Hai-Long Sun, Jingyi Ning +2
Nowadays, real-world applications often face streaming data, which requires the learning system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve thi…
Learning Robust Precipitation Forecaster by Temporal Frame Interpolation
Lu Han, Xu-Yang Chen, Han-Jia Ye +1
Recent advances in deep learning have significantly elevated weather prediction models. However, these models often falter in real-world scenarios due to their sensitivity to spati…
Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective
Han-Jia Ye, Qi-Le Zhou, Huai-Hong Yin +2
Pre-training is prevalent in deep learning for vision and text data, leveraging knowledge from other datasets to enhance downstream tasks. However, for tabular data, the inherent h…
Unlocking the Transferability of Tokens in Deep Models for Tabular Data
Qi-Le Zhou, Han-Jia Ye, Le-Ye Wang +1
Fine-tuning a pre-trained deep neural network has become a successful paradigm in various machine learning tasks. However, such a paradigm becomes particularly challenging with tab…
PILOT: A Pre-Trained Model-Based Continual Learning Toolbox
Hai-Long Sun, Da-Wei Zhou, De-Chuan Zhan +1
While traditional machine learning can effectively tackle a wide range of problems, it primarily operates within a closed-world setting, which presents limitations when dealing wit…
ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse
Yi-Kai Zhang, Lu Ren, Chao Yi +3
The rapid expansion of foundation pre-trained models and their fine-tuned counterparts has significantly contributed to the advancement of machine learning. Leveraging pre-trained…
SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models
Shenghua Wan, Yucen Wang, Minghao Shao +2
Model-based imitation learning (MBIL) is a popular reinforcement learning method that improves sample efficiency on high-dimension input sources, such as images and videos. Followi…
Model Spider: Learning to Rank Pre-Trained Models Efficiently
Yi-Kai Zhang, Ting-Ji Huang, Yao-Xiang Ding +2
Figuring out which Pre-Trained Model (PTM) from a model zoo fits the target task is essential to take advantage of plentiful model resources. With the availability of numerous hete…
Beyond Probability Partitions: Calibrating Neural Networks with Semantic Aware Grouping
Jia-Qi Yang, De-Chuan Zhan, Le Gan
Research has shown that deep networks tend to be overly optimistic about their predictions, leading to an underestimation of prediction errors. Due to the limited nature of data, e…
MrTF: Model Refinery for Transductive Federated Learning
Xin-Chun Li, Yang Yang, De-Chuan Zhan
We consider a real-world scenario in which a newly-established pilot project needs to make inferences for newly-collected data with the help of other parties under privacy protecti…
Preserving Locality in Vision Transformers for Class Incremental Learning
Bowen Zheng, Da-Wei Zhou, Han-Jia Ye +1
Learning new classes without forgetting is crucial for real-world applications for a classification model. Vision Transformers (ViT) recently achieve remarkable performance in Clas…
The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting
Lu Han, Han-Jia Ye, De-Chuan Zhan
Multivariate time series data comprises various channels of variables. The multivariate forecasting models need to capture the relationship between the channels to accurately predi…
Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need
Da-Wei Zhou, Zi-Wen Cai, Han-Jia Ye +2
Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting old ones. Traditional CIL models are trained from scratch to continually acquire knowledge…
On Pseudo-Labeling for Class-Mismatch Semi-Supervised Learning
Lu Han, Han-Jia Ye, De-Chuan Zhan
When there are unlabeled Out-Of-Distribution (OOD) data from other classes, Semi-Supervised Learning (SSL) methods suffer from severe performance degradation and even get worse tha…
Self-Motivated Multi-Agent Exploration
Shaowei Zhang, Jiahan Cao, Lei Yuan +2
In cooperative multi-agent reinforcement learning (CMARL), it is critical for agents to achieve a balance between self-exploration and team collaboration. However, agents can hardl…
Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again
Xin-Chun Li, Wen-Shu Fan, Shaoming Song +4
Knowledge Distillation (KD) aims at transferring the knowledge of a well-performed neural network (the {\it teacher}) to a weaker one (the {\it student}). A peculiar phenomenon is…
Avoid Overfitting User Specific Information in Federated Keyword Spotting
Xin-Chun Li, Jin-Lin Tang, Shaoming Song +5
Keyword spotting (KWS) aims to discriminate a specific wake-up word from other signals precisely and efficiently for different users. Recent works utilize various deep networks to…
Augmentation Component Analysis: Modeling Similarity via the Augmentation Overlaps
Lu Han, Han-Jia Ye, De-Chuan Zhan
Self-supervised learning aims to learn a embedding space where semantically similar samples are close. Contrastive learning methods pull views of samples together and push differen…
A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
Da-Wei Zhou, Qi-Wei Wang, Han-Jia Ye +1
Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a mode…
Selective Cross-Task Distillation
Su Lu, Han-Jia Ye, De-Chuan Zhan
The outpouring of various pre-trained models empowers knowledge distillation by providing abundant teacher resources, but there lacks a developed mechanism to utilize these teacher…