Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJuly 2024
SPeC: A Soft Prompt-Based Calibration on Performance Variability of Large Language Model in Clinical Notes Summarization
Journal of Biomedical Informatics (JOBI), Volume 151, Issue CMar 2024https://doi.org/10.1016/j.jbi.2024.104606AbstractElectronic health records (EHRs) store an extensive array of patient information, encompassing medical histories, diagnoses, treatments, and test outcomes. These records are crucial for enabling healthcare providers to make well-informed ...
Graphical abstractDisplay Omitted
- research-articleJune 2024
Dirichlet energy constrained learning for deep graph neural networks
NIPS '21: Proceedings of the 35th International Conference on Neural Information Processing SystemsDecember 2021, Article No.: 1671, Pages 21834–21846Graph neural networks (GNNs) integrate deep architectures and topological structure modeling in an effective way. However, the performance of existing GNNs would decrease significantly when they stack many layers, because of the over-smoothing issue. ...
- research-articleJune 2024
Fairness via representation neutralization
NIPS '21: Proceedings of the 35th International Conference on Neural Information Processing SystemsDecember 2021, Article No.: 925, Pages 12091–12103Existing bias mitigation methods for DNN models primarily work on learning debiased encoders. This process not only requires a lot of instance-level annotations for sensitive attributes, it also does not guarantee that all fairness sensitive information ...
- research-articleMay 2024
Fair graph distillation
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 3535, Pages 80644–80660As graph neural networks (GNNs) struggle with large-scale graphs due to high computational demands, graph data distillation promises to alleviate this issue by distilling a large real graph into a smaller distilled graph while maintaining comparable ...
- research-articleMay 2024
Setting the trap: capturing and defeating backdoors in pretrained language models through honeypots
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 3199, Pages 73191–73210In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the adversaries can embed ...
-
- research-articleMay 2024
Chasing fairness under distribution shift: a model weight perturbation approach
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 2793, Pages 63931–63944Fairness in machine learning has attracted increasing attention in recent years. The fairness methods improving algorithmic fairness for in-distribution data may not perform well under distribution shifts. In this paper, we first theoretically ...
- research-articleMay 2024
One less reason for filter-pruning: gaining free adversarial robustness with structured grouped kernel pruning
- Shaochen (Henry) Zhong,
- Zaichuan You,
- Jiamu Zhang,
- Sebastian Zhao,
- Zachary LeClaire,
- Zirui Liu,
- Daochen Zha,
- Vipin Chaudhary,
- Shuai Xu,
- Xia Hu
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 2712, Pages 62032–62061Densely structured pruning methods utilizing simple pruning heuristics can deliver immediate compression and acceleration benefits with acceptable benign performances. However, empirical findings indicate such naïvely pruned networks are extremely ...
- research-articleMay 2024
Winner-take-all column row sampling for memory efficient adaptation of language model
- Zirui Liu,
- Guanchu Wang,
- Shaochen Zhong,
- Zhaozhuo Xu,
- Daochen Zha,
- Ruixiang Tang,
- Zhimeng Jiang,
- Kaixiong Zhou,
- Vipin Chaudhary,
- Shuai Xu,
- Xia Hu
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 150, Pages 3402–3424As the model size grows rapidly, fine-tuning the large pre-trained language model has become increasingly difficult due to its extensive memory usage. Previous works usually focus on reducing the number of trainable parameters in the network. While the ...
- tutorialApril 2024
Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond
- Jingfeng Yang,
- Hongye Jin,
- Ruixiang Tang,
- Xiaotian Han,
- Qizhang Feng,
- Haoming Jiang,
- Shaochen Zhong,
- Bing Yin,
- Xia Hu
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 6Article No.: 160, Pages 1–32https://doi.org/10.1145/3649506This article presents a comprehensive and practical guide for practitioners and end-users working with Large Language Models (LLMs) in their downstream Natural Language Processing (NLP) tasks. We provide discussions and insights into the usage of LLMs ...
- research-articleApril 2024
DreamShard: generalizable embedding table placement for recommender systems
- Daochen Zha,
- Louis Feng,
- Qiaoyu Tan,
- Zirui Liu,
- Kwei-Herng Lai,
- Bhargav Bhushanam,
- Yuandong Tian,
- Arun Kejariwal,
- Xia Hu
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsNovember 2022, Article No.: 1105, Pages 15190–15203We study embedding table placement for distributed recommender systems, which aims to partition and place the tables on multiple hardware devices (e.g., GPUs) to balance the computation and communication costs. Although prior work has explored learning-...
- research-articleApril 2024
A comprehensive study on large-scale graph training: benchmarking and rethinking
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsNovember 2022, Article No.: 388, Pages 5376–5389Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs). Due to the nature of evolving graph structures into the training process, vanilla GNNs usually fail to scale up, limited by the GPU memory space. Up to now, ...
- research-articleMarch 2024
The Science of Detecting LLM-Generated Text
Communications of the ACM (CACM), Volume 67, Issue 4April 2024, Pages 50–59https://doi.org/10.1145/3624725While many detection methods have been proposed, understanding the challenges is far more daunting.
- research-articleMarch 2024
AutoKeras: an AutoML library for deep learning
The Journal of Machine Learning Research (JMLR), Volume 24, Issue 1Article No.: 6, Pages 169–174To use deep learning, one needs to be familiar with various software tools like TensorFlow or Keras, as well as various model architecture and optimization best practices. Despite recent progress in software usability, deep learning remains a highly ...
- research-articleDecember 2023
Shortcut Learning of Large Language Models in Natural Language Understanding
Communications of the ACM (CACM), Volume 67, Issue 1January 2024, Pages 110–120https://doi.org/10.1145/3596490Shortcuts often hinder the robustness of large language models.
- short-paperOctober 2023
Exposing Model Theft: A Robust and Transferable Watermark for Thwarting Model Extraction Attacks
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementOctober 2023, Pages 4315–4319https://doi.org/10.1145/3583780.3615211The increasing prevalence of Deep Neural Networks (DNNs) in cloud-based services has led to their widespread use through various APIs. However, recent studies reveal the susceptibility of these public APIs to model extraction attacks, where adversaries ...
- research-articleOctober 2023
Tackling Diverse Minorities in Imbalanced Classification
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementOctober 2023, Pages 1178–1187https://doi.org/10.1145/3583780.3615071Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers. When working with large datasets, the imbalanced issue can be further exacerbated, making it exceptionally difficult ...
- short-paperOctober 2023
DiscoverPath: A Knowledge Refinement and Retrieval System for Interdisciplinarity on Biomedical Research
- Yu-Neng Chuang,
- Guanchu Wang,
- Chia-Yuan Chang,
- Kwei-Herng Lai,
- Daochen Zha,
- Ruixiang Tang,
- Fan Yang,
- Alfredo Costilla Reyes,
- Kaixiong Zhou,
- Xiaoqian Jiang,
- Xia Hu
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementOctober 2023, Pages 5021–5025https://doi.org/10.1145/3583780.3614739The exponential growth in scholarly publications necessitates advanced tools for efficient article retrieval, especially in interdisciplinary fields where diverse terminologies are used to describe similar research. Traditional keyword-based search ...
- research-articleOctober 2023
Can Attention Be Used to Explain EHR-Based Mortality Prediction Tasks: A Case Study on Hemorrhagic Stroke
BCB '23: Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health InformaticsSeptember 2023, Article No.: 26, Pages 1–6https://doi.org/10.1145/3584371.3613002Stroke is a significant cause of mortality and morbidity, necessitating early predictive strategies to minimize risks. Traditional methods for evaluating patients, such as Acute Physiology and Chronic Health Evaluation (APACHE II, IV) and Simplified ...
- ArticleSeptember 2023
Deep Serial Number: Computational Watermark for DNN Intellectual Property Protection
Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo TrackSep 2023, Pages 157–173https://doi.org/10.1007/978-3-031-43427-3_10AbstractIn this paper, we present DSN (Deep Serial Number), a simple yet effective watermarking algorithm designed specifically for deep neural networks (DNNs). Unlike traditional methods that incorporate identification signals into DNNs, our approach ...
- ArticleSeptember 2023
Mitigating Algorithmic Bias with Limited Annotations
Machine Learning and Knowledge Discovery in Databases: Research TrackSep 2023, Pages 241–258https://doi.org/10.1007/978-3-031-43415-0_15AbstractExisting work on fairness modeling commonly assumes that sensitive attributes for all instances are fully available, which may not be true in many real-world applications due to the high cost of acquiring sensitive information. When sensitive ...