Wei Cheng

Wei Cheng

Auto-generated profile, based on publicly available information

Wei Cheng

NEC Laboratories America, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 October 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
LCLing Chen
Ling Chen
XZXujiang Zhao
Xujiang Zhao
JLJiaying Lu
Jiaying Lu
CDChengyuan Deng
Chengyuan Deng
CZCan Zheng
Can Zheng
LZLiang Zhao
Liang Zhao
Large language models (LLMs) have significantly advanced the field of natural language processing (NLP), providing a highly useful, task-agnostic foundation for a wide range of applications. However, directly applying LLMs to solve sophisticated problems in specific domains meets many hurdles, caused by the heterogeneity of domain data, the sophistication of domain knowledge, the uniqueness of domain objectives, and the diversity of the constraints (e.g., various social norms, cultural conformity, religious beliefs, and ethical standards in the domain applications). Domain specification techniques are key to making large language models disruptive in many applications. Specifically, to solve these hurdles, there has been a notable increase in research and practices conducted in recent years on the domain specialization of LLMs. This emerging field of study, with its substantial potential for impact, necessitates a comprehensive and systematic review to summarize better and guide ongoing work in this area. In this article, we present a comprehensive survey on domain specification techniques for large language models, an emerging direction critical for large language model applications. First, we propose a systematic taxonomy that categorizes the LLM domain-specialization techniques based on the accessibility to LLMs and summarizes the framework for all the subcategories as well as their relations and differences to each other. Second, we present an extensive taxonomy of critical application domains that can benefit dramatically from specialized LLMs, discussing their practical significance and open challenges. Last, we offer our insights into the current research status and future trends in this area.

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
DLDongshegn Luo
Dongshegn Luo
WCWei Cheng
Wei Cheng
YWYingheng Wang
Yingheng Wang
DXDongkuan Xu
Dongkuan Xu
JNJingchao Ni
Jingchao Ni
XZXiang Zhang
Xiang Zhang
Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key component of contrastive learning is to select appropriate augmentations imposing some priors to construct feasible positive samples, such that an encoder can be trained to learn robust and discriminative representations. Unlike image and language domains where "desired'' augmented samples can be generated with the rule of thumb guided by prefabricated human priors, the ad-hoc manual selection of time series augmentations is hindered by their diverse and human-unrecognizable temporal structures. How to find the desired augmentations of time series data that are meaningful for given contrastive learning tasks and datasets remains an open question. In this work, we address the problem by encouraging both high fidelity and variety based on information theory. A theoretical analysis leads to the criteria for selecting feasible data augmentations. On top of that, we propose a new contrastive learning approach with information-aware augmentations, InfoTS, that adaptively selects optimal augmentations for time series representation learning. Experiments on various datasets show highly competitive performance with up to a 12.0% reduction in MSE on forecasting tasks and up to 3.7% relative improvement in accuracy on classification tasks over the leading baselines.

1 January 2024
Verified
Conference Paper
Open access
PDF file
XYXianjun Yang
Xianjun Yang
LPLiangming Pan
Liangming Pan
XZXuandong Zhao
Xuandong Zhao
HCHaifeng Chen
Haifeng Chen
LPLinda Ruth Petzold
Linda Ruth Petzold
WCWei Cheng
Wei Cheng
Xianjun Yang, Liangming Pan, Xuandong Zhao, Haifeng Chen, Linda Ruth Petzold, William Yang Wang, Wei Cheng. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

13 August 2016
Verified
Conference Paper
Open access
WCWei Cheng
Wei Cheng
KZKai Zhang
Kai Zhang
HCHaifeng Chen
Haifeng Chen
GJGuofei Jiang
Guofei Jiang
ZCZhengzhang Chen
Zhengzhang Chen
WWWei Wang
Wei Wang
Modern world has witnessed a dramatic increase in our ability to collect, transmit and distribute real-time monitoring and surveillance data from large-scale information systems and cyber-physical systems. Detecting system anomalies thus attracts significant amount of interest in many fields such as security, fault management, and industrial optimization. Recently, invariant network has shown to be a powerful way in characterizing complex system behaviours. In the invariant network, a node represents a system component and an edge indicates a stable, significant interaction between two components. Structures and evolutions of the invariance network, in particular the vanishing correlations, can shed important light on locating causal anomalies and performing diagnosis. However, existing approaches to detect causal anomalies with the invariant network often use the percentage of vanishing correlations to rank possible casual components, which have several limitations: 1) fault propagation in the network is ignored; 2) the root casual anomalies may not always be the nodes with a high-percentage of vanishing correlations; 3) temporal patterns of vanishing correlations are not exploited for robust detection. To address these limitations, in this paper we propose a network diffusion based framework to identify significant causal anomalies and rank them. Our approach can effectively model fault propagation over the entire invariant network, and can perform joint inference on both the structural, and the time-evolving broken invariance patterns. As a result, it can locate high-confidence anomalies that are truly responsible for the vanishing correlations, and can compensate for unstructured measurement noise in the system. Extensive experiments on synthetic datasets, bank information system datasets, and coal plant cyber-physical system datasets demonstrate the effectiveness of our approach.

1 January 2024
Verified
Conference Paper
Open access
PDF file
YXYijia Xiao
Yijia Xiao
YJYiqiao Jin
Yiqiao Jin
YBYushi Bai
Yushi Bai
YWYue Wu
Yue Wu
XYXianjun Yang
Xianjun Yang
WCWei Cheng
Wei Cheng
Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

21 June 2018 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
LLLiang Lan
Liang Lan
ZWZhuang Wang
Zhuang Wang
SZShandian Zhe
Shandian Zhe
WCWei Cheng
Wei Cheng
JWJun Wang
Jun Wang
KZKai Zhang
Kai Zhang
Kernel support vector machines (SVMs) deliver state-of-the-art results in many real-world nonlinear classification problems, but the computational cost can be quite demanding in order to maintain a large number of support vectors. Linear SVM, on the other hand, is highly scalable to large data but only suited for linearly separable problems. In this paper, we propose a novel approach called low-rank linearized SVM to scale up kernel SVM on limited resources. Our approach transforms a nonlinear SVM to a linear one via an approximate empirical kernel map computed from efficient kernel low-rank decompositions. We theoretically analyze the gap between the solutions of the approximate and optimal rank-k kernel map, which in turn provides guidance on the sampling scheme of the Nyström approximation. Furthermore, we extend it to a semisupervised metric learning scenario in which partially labeled samples can be exploited to further improve the quality of the low-rank embedding. Our approach inherits rich representability of kernel SVM and high efficiency of linear SVM. Experimental results demonstrate that our approach is more robust and achieves a better tradeoff between model representability and scalability against state-of-the-art algorithms for large-scale SVMs.