no code implementations • 1 May 2024 • Mingchen Li, Halil Kilicoglu, Hua Xu, Rui Zhang
Large Language Models (LLMs) have swiftly emerged as vital resources for different applications in the biomedical and healthcare domains; however, these models encounter issues such as generating inaccurate information or hallucinations.
1 code implementation • 23 Apr 2024 • Yang Tan, Mingchen Li, Bingxin Zhou, Bozitao Zhong, Lirong Zheng, Pan Tan, Ziyi Zhou, Huiqun Yu, Guisheng Fan, Liang Hong
Fine-tuning Pre-trained protein language models (PLMs) has emerged as a prominent strategy for enhancing downstream prediction tasks, often outperforming traditional supervised learning approaches.
no code implementations • 16 Feb 2024 • Mingchen Li, Chen Ling, Rui Zhang, Liang Zhao
To address this, in this work, we introduce a Condensed Transition Graph Framework for Zero-Shot Link Prediction (CTLP), which encodes all the paths' information in linear time complexity to predict unseen relations between entities, attaining both efficiency and information preservation.
no code implementations • 3 Feb 2024 • Ziyi Zhou, Liang Zhang, Yuanxi Yu, Mingchen Li, Liang Hong, Pan Tan
Accurately modeling the protein fitness landscapes holds great importance for protein engineering.
no code implementations • 25 Jan 2024 • Xuechen Zhang, Mingchen Li, Jiasi Chen, Christos Thrampoulidis, Samet Oymak
Confirming this, under a gaussian mixture setting, we show that the optimal SVM classifier for balanced accuracy needs to be adaptive to the class attributes.
no code implementations • 27 Oct 2023 • Mingchen Li, Huixue Zhou, Rui Zhang
Biomedical triple extraction systems aim to automatically extract biomedical entities and relations between entities.
1 code implementation • 26 Oct 2023 • Yang Tan, Mingchen Li, Pan Tan, Ziyi Zhou, Huiqun Yu, Guisheng Fan, Liang Hong
Moreover, despite the wealth of benchmarks and studies in the natural language community, there remains a lack of a comprehensive benchmark for systematically evaluating protein language model quality.
no code implementations • 23 Oct 2023 • Ying Liu, Haozhu Wang, Huixue Zhou, Mingchen Li, Yu Hou, Sicheng Zhou, Fang Wang, Rama Hoetzlein, Rui Zhang
It has gained significant attention in the field of Natural Language Processing (NLP) due to its ability to learn optimal strategies for tasks such as dialogue systems, machine translation, and question-answering.
no code implementations • 6 Sep 2023 • Keyu Chen, Di Zhuang, Mingchen Li, J. Morris Chang
Experiments on English-German and English-Romanian translation show that: (i) Epi-Curriculum improves both model's robustness and adaptability in seen and unseen domains; (ii) Our episodic training framework enhances the encoder and decoder's robustness to domain shift.
1 code implementation • 3 Sep 2023 • Yang Tan, Mingchen Li, Zijie Huang, Huiqun Yu, Guisheng Fan
Generative large language models (LLMs) have shown great success in various applications, including question-answering (QA) and dialogue systems.
no code implementations • 24 Jul 2023 • Pan Tan, Mingchen Li, Yuanxi Yu, Fan Jiang, Lirong Zheng, Banghao Wu, Xinyu Sun, Liqi Kang, Jie Song, Liang Zhang, Yi Xiong, Wanli Ouyang, Zhiqiang Hu, Guisheng Fan, Yufeng Pei, Liang Hong
Designing protein mutants with high stability and activity is a critical yet challenging task in protein engineering.
no code implementations • 10 Jul 2023 • Xuechen Zhang, Mingchen Li, Xiangyu Chang, Jiasi Chen, Amit K. Roy-Chowdhury, Ananda Theertha Suresh, Samet Oymak
These insights on scale and modularity motivate a new federated learning approach we call "You Only Load Once" (FedYolo): The clients load a full PTF model once and all future updates are accomplished through communication-efficient modules with limited catastrophic-forgetting, where each task is assigned to its own module.
no code implementations • 1 Jul 2023 • Mingchen Li, Rui Zhang
Recent advancements in language models (LMs) have led to the emergence of powerful models such as Small LMs (e. g., T5) and Large LMs (e. g., GPT-4).
1 code implementation • 2 Jun 2023 • Davoud Ataee Tarzanagh, Mingchen Li, Pranay Sharma, Samet Oymak
Stochastic approximation with multiple coupled sequences (MSA) has found broad applications in machine learning as it encompasses a rich class of problems including bilevel optimization (BLO), multi-level compositional optimization (MCO), and reinforcement learning (specifically, actor-critic methods).
no code implementations • 29 May 2023 • Mingchen Li, Yang Ye, Jeremy Yeung, Huixue Zhou, Huaiyuan Chu, Rui Zhang
Contrastive learning has become a popular solution for few-shot Name Entity Recognization (NER).
no code implementations • 26 Apr 2023 • Mingchen Li, Lifu Huang
Open domain entity state tracking aims to predict reasonable state changes of entities (i. e., [attribute] of [entity] was [before_state] and [after_state] afterwards) given the action descriptions.
no code implementations • 7 Apr 2023 • Pan Tan, Mingchen Li, Liang Zhang, Zhiqiang Hu, Liang Hong
We introduce TemPL, a novel deep learning approach for zero-shot prediction of protein stability and activity, harnessing temperature-guided language modeling.
no code implementations • 29 Dec 2022 • Mingchen Li, Liqi Kang, Yi Xiong, Yu Guang Wang, Guisheng Fan, Pan Tan, Liang Hong
Here, we develop SESNet, a supervised deep-learning model to predict the fitness for protein mutants by leveraging both sequence and structure information, and exploiting attention mechanism.
1 code implementation • 28 May 2022 • Mingchen Li, Di Zhuang, J. Morris Chang
MC-GEN applies multi-level clustering and differential private generative model to improve the utility of synthetic data.
3 code implementations • 4 May 2022 • Davoud Ataee Tarzanagh, Mingchen Li, Christos Thrampoulidis, Samet Oymak
Standard federated optimization methods successfully apply to stochastic problems with single-level structure.
1 code implementation • 16 Apr 2022 • Mingchen Li, Junfan Chen, Samuel Mensah, Nikolaos Aletras, Xiulong Yang, Yang Ye
Thus, in this paper, we propose a Hierarchical N-Gram framework for Zero-Shot Link Prediction (HNZSLP), which considers the dependencies among character n-grams of the relation surface name for ZSLP.
1 code implementation • COLING 2022 • Mingchen Li, Shihao Ji
Therefore, this paper focuses on query graph generation from natural language questions.
1 code implementation • 3 Mar 2022 • Yingcong Li, Mingchen Li, M. Salman Asif, Samet Oymak
In continual learning (CL), the goal is to design models that can learn a sequence of tasks without catastrophic forgetting.
1 code implementation • 7 Feb 2022 • Di Zhuang, Mingchen Li, J. Morris Chang
As such, it motivates the researchers to conduct distributed deep learning, where the data user would like to build DL models using the data segregated across multiple different data owners.
1 code implementation • NeurIPS 2021 • Mingchen Li, Xuechen Zhang, Christos Thrampoulidis, Jiasi Chen, Samet Oymak
Our experimental findings are complemented with theoretical insights on loss function design and the benefits of train-validation split.
no code implementations • 29 Apr 2021 • Samet Oymak, Mingchen Li, Mahdi Soltanolkotabi
In this approach, it is common to use bilevel optimization where one optimizes the model weights over the training data (inner problem) and various hyperparameters such as the configuration of the architecture over the validation data (outer problem).
no code implementations • 16 Nov 2020 • Yao-Chun Chan, Mingchen Li, Samet Oymak
In parallel, recent developments in self-supervised and semi-supervised learning (S4L) provide powerful techniques, based on data-augmentation, contrastive learning, and self-training, that enable superior utilization of unlabeled data which led to a significant reduction in required labeling in the standard machine learning benchmarks.
no code implementations • 19 Jun 2020 • Mingchen Li, Yahya Sattar, Christos Thrampoulidis, Samet Oymak
Model pruning is an essential procedure for building compact and computationally-efficient machine learning models.
no code implementations • 9 Feb 2020 • Mingchen Li, Gabtone. Clinton, Yijia Miao, Feng Gao
Short text is becoming more and more popular on the web, such as Chat Message, SMS and Product Reviews.
no code implementations • 5 Feb 2020 • Mingchen Li, Zili Zhou, Yanna Wang
By using them, we found that these word networks have low accuracy and coverage, and cannot completely portray the semantic network of PWN.
no code implementations • 25 Sep 2019 • Samet Oymak, Zalan Fabian, Mingchen Li, Mahdi Soltanolkotabi
We show that over the information space learning is fast and one can quickly train a model with zero training loss that can also generalize well.
no code implementations • 12 Jun 2019 • Samet Oymak, Zalan Fabian, Mingchen Li, Mahdi Soltanolkotabi
We show that over the information space learning is fast and one can quickly train a model with zero training loss that can also generalize well.
1 code implementation • 27 Mar 2019 • Mingchen Li, Mahdi Soltanolkotabi, Samet Oymak
In particular, we prove that: (i) In the first few iterations where the updates are still in the vicinity of the initialization gradient descent only fits to the correct labels essentially ignoring the noisy labels.
1 code implementation • 25 Sep 2017 • Di Zhuang, J. Morris Chang, Mingchen Li
Community detection is of great importance for online social network analysis.
Social and Information Networks Cryptography and Security