Výsledky vyhledávání - "Liang, Daojun"

Report

Multi-Head Encoding for Extreme Label Classification

Autor: Liang, Daojun, Zhang, Haixia, Yuan, Dongfeng, Zhang, Minggao

The number of categories of instances in the real world is normally huge, and each instance may contain multiple labels. To distinguish these massive labels utilizing machine learning, eXtreme Label Classification (XLC) has been established. However,

Externí odkaz: http://arxiv.org/abs/2412.10182

Zobrazit plný text záznamu

Report

Act Now: A Novel Online Forecasting Framework for Large-Scale Streaming Data

Autor: Liang, Daojun, Zhang, Haixia, Wang, Jing, Yuan, Dongfeng, Zhang, Minggao

In this paper, we find that existing online forecasting methods have the following issues: 1) They do not consider the update frequency of streaming data and directly use labels (future signals) to update the model, leading to information leakage. 2)

Externí odkaz: http://arxiv.org/abs/2412.00108

Zobrazit plný text záznamu

Report

DistPred: A Distribution-Free Probabilistic Inference Method for Regression and Forecasting

Autor: Liang, Daojun, Zhang, Haixia, Yuan, Dongfeng

Traditional regression and prediction tasks often only provide deterministic point estimates. To estimate the uncertainty or distribution information of the response variable, methods such as Bayesian inference, model ensembling, or MC Dropout are ty

Externí odkaz: http://arxiv.org/abs/2406.11397

Zobrazit plný text záznamu

Report

Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals

Autor: Liang, Daojun, Zhang, Haixia, Yuan, Dongfeng, Zhang, Bingzheng, Zhang, Minggao

In this paper, we find that ubiquitous time series (TS) forecasting models are prone to severe overfitting. To cope with this problem, we embrace a de-redundancy approach to progressively reinstate the intrinsic values of TS for future intervals. Spe

Externí odkaz: http://arxiv.org/abs/2402.02332

Zobrazit plný text záznamu

Report

Does Long-Term Series Forecasting Need Complex Attention and Extra Long Inputs?

Autor: Liang, Daojun, Zhang, Haixia, Yuan, Dongfeng, Ma, Xiaoyan, Li, Dongyang, Zhang, Minggao

As Transformer-based models have achieved impressive performance on various time series tasks, Long-Term Series Forecasting (LTSF) tasks have also received extensive attention in recent years. However, due to the inherent computational complexity and

Externí odkaz: http://arxiv.org/abs/2306.05035

Zobrazit plný text záznamu