Author name cluster

Yu Yan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

EAAI Journal 2025 Journal Article

Multi-scale fuzzy self-attention network for hyperspectral image classification with small-samples

Ziyi Li
Jindong Xu
Qianpeng Chong
Yu Yan

—With the widespread application of convolutional neural networks (CNN), significant breakthroughs have been achieved in hyperspectral image (HSI) classification. However, the lack of training samples remains one of the primary factors contributing to low classification performance. Moreover, HSIs may be affected by factors such as lighting conditions, environmental variations, and photographing distances during the collecting process, inevitably introducing noise. This noise significantly increases the uncertainty of the classification process, particularly in small sample scenarios. To alleviate these issues, a multi-scale fuzzy self-attention network (MFSAN) is proposed. Firstly, a multi-scale fuzzy embedding module (MFEM) is designed to effectively model fuzzy dependencies between features through three parallel paths, mitigating noise-induced uncertainty across multiple scales. Secondly, inspired by the principles of Transformers, a weighted dual-distance combined self-attention module (WD2CAM) is proposed to enhance global context representation by utilizing a novel spectral similarity measure. Finally, a new multiple feature extraction module is developed to fully exploit the rich information of HSIs under limited training samples. This module extracts spectral, spatial, and spectral-spatial features using multiple three-dimensional convolutions with different receptive fields. Experimental results on three datasets demonstrate that MFSAN achieves superior classification accuracy compared to state-of-the-art methods, with performance improvements in overall accuracy (OA) ranging from 1. 43 % to 9. 84 % under 1 % training samples.

Details DOI

ECAI Conference 2024 Conference Paper

Enhancing Stance Detection on Social Media via Core Views Discovery

Yu Yan
Yinghan Shen
Teli Liu
Xuhui Jiang
Dechun Yin

Stance detection aims to identify the expressed attitude towards a target from the text, which is significant for learning public cognition from social media. The short and implicit nature of social media users’ expressions potentially results in the stance understanding bias of the model. To address this problem, introducing external background information is helpful to mitigate these biases and enhance explainability. The core view, reflecting the motivations and reasons behind an individual’s stance toward the target, can be summarized and extracted from collective tweets, which can serve as a reference for stance detection. In this study, we propose the Stance Detection via Core View Discovery (SD-CVM), where the core views are used for background information modeling. Specifically, we construct a joint classifier combining the semantic understanding of tweets and their relevant core views from the public. We utilize the Large Language Model (LLM) to extract core views with stances from tweets and use these core views as background references for tweets. To further optimize the tweet understanding, we develop the contrastive and rebalancing mechanism by incorporating stance supervision signals for training. Experiments on two representative datasets demonstrate the excellent performance of our method.

Details

ICML Conference 2021 Conference Paper

BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining

Weizhen Qi
Yeyun Gong
Jian Jiao 0007
Yu Yan
Weizhu Chen
Dayiheng Liu
Kewen Tang
Houqiang Li

In this paper, we propose BANG, a new pretraining model to Bridge the gap between Autoregressive (AR) and Non-autoregressive (NAR) Generation. AR and NAR generation can be uniformly regarded as to what extent previous tokens can be attended, and BANG bridges AR and NAR generation through designing a novel model structure for large-scale pre-training. A pretrained BANG model can simultaneously support AR, NAR, and semi-NAR generation to meet different requirements. Experiments on question generation (SQuAD 1. 1), summarization (XSum), and dialogue generation (PersonaChat) show that BANG improves NAR and semi-NAR performance significantly as well as attaining comparable performance with strong AR pretrained models. Compared with the semi-NAR strong baselines, BANG achieves absolute improvements of 14. 01 and 5. 24 in the overall scores of SQuAD 1. 1 and XSum, respectively. In addition, BANG achieves absolute improvements of 10. 73, 6. 39, and 5. 90 in the overall scores of SQuAD, XSUM, and PersonaChat compared with the NAR strong baselines, respectively. Our code will be made publicly available.

Details

AAAI Conference 2021 Conference Paper

Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference

Yichao Zhou
Yu Yan
Rujun Han
J. Harry Caufield
Kai-Wei Chang
Yizhou Sun
Peipei Ping
Wei Wang

There has been a steady need in the medical community to precisely extract the temporal relations between clinical events. In particular, temporal information can facilitate a variety of downstream applications such as case report retrieval and medical question answering. However, existing methods either require expensive feature engineering or are incapable of modeling the global relational dependencies among the events. In this paper, we propose Clinical Temporal ReLation Exaction with Probabilistic Soft Logic Regularization and Global Inference (CTRL-PG), a novel method to tackle the problem at the document level. Extensive experiments on two benchmark datasets, I2B2-2012 and TB-Dense, demonstrate that CTRL-PG significantly outperforms baseline methods for temporal relation extraction.

PDF Details

ICML Conference 2021 Conference Paper

EL-Attention: Memory Efficient Lossless Attention for Generation

Yu Yan
Jiusheng Chen
Weizhen Qi
Nikhil Bhendawade
Yeyun Gong
Nan Duan 0001
Ruofei Zhang

Transformer model with multi-head attention requires caching intermediate results for efficient inference in generation tasks. However, cache brings new memory-related costs and prevents leveraging larger batch size for faster speed. We propose memory-efficient lossless attention (called EL-attention) to address this issue. It avoids heavy operations for building multi-head keys and values, cache for them is not needed. EL-attention constructs an ensemble of attention results by expanding query while keeping key and value shared. It produces the same result as multi-head attention with less GPU memory and faster inference speed. We conduct extensive experiments on Transformer, BART, and GPT-2 for summarization and question generation tasks. The results show EL-attention speeds up existing models by 1. 6x to 5. 3x without accuracy loss.

Details