1 code implementation • 19 Apr 2024 • Biyang Guo, He Wang, Wenyilin Xiao, Hong Chen, Zhuxin Lee, Songqiao Han, Hailiang Huang
In the burgeoning field of Large Language Models (LLMs) like ChatGPT and LLaMA, Prompt Engineering (PE) is renowned for boosting zero-shot or in-context learning (ICL) through prompt modifications.
1 code implementation • 6 Dec 2023 • Xu Yao, Shuang Liang, Songqiao Han, Hailiang Huang
To address data scarcity and imbalance in MPP, some studies have adopted Graph Neural Networks (GNN) as an encoder to extract commonalities from molecular graphs.
3 code implementations • NeurIPS 2023 • Minqi Jiang, Chaochuan Hou, Ao Zheng, Songqiao Han, Hailiang Huang, Qingsong Wen, Xiyang Hu, Yue Zhao
Deep learning (DL) techniques have recently found success in anomaly detection (AD) across various fields such as finance, medical services, and cloud computing.
1 code implementation • 26 Jun 2023 • Minqi Jiang, Songqiao Han, Hailiang Huang
In this paper, we propose to optimize the anomaly scoring function from the view of score distribution, thus better retaining the diversity and more fine-grained information of input data, especially when the unlabeled data contains anomaly noises in more practical AD scenarios.
2 code implementations • 9 Feb 2023 • Minqi Jiang, Chaochuan Hou, Ao Zheng, Xiyang Hu, Songqiao Han, Hailiang Huang, Xiangnan He, Philip S. Yu, Yue Zhao
Anomaly detection (AD) is a crucial task in machine learning with various applications, such as detecting emerging diseases, identifying financial frauds, and detecting fake news.
2 code implementations • 18 Nov 2022 • Biyang Guo, Yeyun Gong, Yelong Shen, Songqiao Han, Hailiang Huang, Nan Duan, Weizhu Chen
We introduce GENIUS: a conditional text generation model using sketches as input, which can fill in the missing contexts for a given sketch (key information consisting of textual spans, phrases, or words, concatenated by mask tokens).
no code implementations • 23 Sep 2022 • Ziyuan Wang, Hailiang Huang, Songqiao Han
Current text classification methods typically encode the text merely into embedding before a naive or complicated classifier, which ignores the suggestive information contained in the label text.
1 code implementation • 4 Sep 2022 • Biyang Guo, Songqiao Han, Hailiang Huang
Different words may play different roles in text classification, which inspires us to strategically select the proper roles for text augmentation.
5 code implementations • 19 Jun 2022 • Songqiao Han, Xiyang Hu, Hailiang Huang, Mingqi Jiang, Yue Zhao
Given a long list of anomaly detection algorithms developed in the last few decades, how do they perform with regard to (i) varying levels of supervision, (ii) different types of anomalies, and (iii) noisy and corrupted data?
no code implementations • 9 Nov 2021 • Songqiao Han, Hailiang Huang, Jiangwei Liu
These methods encode news content on the word level and jointly train the attention parameters in the recommendation network, leading to more corpora being required to train the model.
no code implementations • 9 Nov 2021 • Songqiao Han, Hailiang Huang, Jiangwei Liu, Shengsheng Xiao
Social media platforms may provide potential space for discourses that contain hate speech, and even worse, can act as a propagation mechanism for hate crimes.
1 code implementation • 9 Dec 2020 • Biyang Guo, Songqiao Han, Xiao Han, Hailiang Huang, Ting Lu
LCM can learn label confusion to capture semantic overlap among labels by calculating the similarity between instances and labels during training and generate a better label distribution to replace the original one-hot label vector, thus improving the final classification performance.