Xujiang Zhao
I am a researcher at NEC Laboratories America. I received the Ph.D. in Computer Science Department at The University of Texas at Dallas, in 2022. My advisor is Prof. Feng Chen. I also got an MS at the University of Science and Technology of China (USTC) and a bachelor at Chongqing University in China.
Email  / 
CV  / 
Google Scholar  / 
LinkedIn  / 
Github
|
|
Quote
" The fear of the LORD is the beginning of wisdom " - Psalms 111:10
|
News
09/2024: one paper got accepted by EMNLP 2024
04/2024: one paper got accepted by IJCAI 2024
03/2024: Our LLM survey paper was cited by 2024 Economic Report of the President of the United States
03/2024: Our Uncertainty Reasoning workshop was accepted at KDD 2024
03/2024: two paper got accepted by NAACL 2024
02/2024: I will serve as the PC/reviewer of ICLR,AAAI,KDD,ICML,ARR,COLM 2024
10/2023: one paper got accepted by EMNLP 2023
09/2023: one survey paper got accepted by Information Fusion
08/2023: two paper got accepted by CIKM 2023
03/2023: Our Uncertainty Reasoning workshop was accepted at KDD 2023
02/2023: one paper got accepted by ICASSP 2023
01/2023: I am overjoyed to have embraced Christianity
09/2022: Our Uncertainty Reasoning workshop was accepted at AAAI 2023
08/2022: one paper got accepted by ICDM 2022
08/2022: one paper got accepted by CIKM 2022
07/2022: I will serve as the PC/reviewer of ICLR,AAAI,KDD,ICML,NeurIPS 2023
01/2022: one paper got accepted by ICASSP 2022
09/2021: one paper got accepted by NeurIPS 2021
08/2021: one paper got accepted by EMNLP 2021
06/2021: I will serve as the PC/reviewer of ICLR,WSDM,AAAI,KDD,ICML,NeurIPS 2022
01/2021: one paper got accepted by WWW 2021
12/2020: one paper got accepted by AAAI 2021
11/2020: I will serve as the PC Member of KDD, NeurIPS 2021
09/2020: two paper got accepted by NeurIPS 2020, one Spotlight, one Poster
|
Experience
Reseracher at NEC Laboratories America (Princeton, NJ) since 2022 summer
Reserach intern at NEC Laboratories America (Princeton, NJ) during 2021 summer
Reserach intern at Alibaba Damo Academy (Seattle, WA) during 2019 summer
|
Research
I'm interested in machine learning and data mining, especially in Uncertainty Estimation, Large Language Models, Reinforcement Learning, Natural Language Processing, and Graph Neural Networks.
Representative papers are highlighted.
|
|
Large Language Models Can Be Contextual Privacy Protection Learners
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
EMNLP, 2024
paper /
code /
In this paper, we present a comprehensive exploration of strategies for fine-tuning Large Language Models (LLMs) to incorporate domain-specific knowledge while upholding data privacy.
|
|
Towards Counterfactual Fairness-aware Domain Generalization in Changing Environments
Yujie Lin, Chen Zhao, Minglai Shao, Baoluo Meng, Xujiang Zhao, Haifeng Chen
IJCAI, 2024
paper /
This paper has proposed a novel framework, DCFDG, to address issues of fairness within continuously evolving dynamic environments.
|
|
Pruning as a Domain-specific LLM Extractor
Nan Zhang, Yanchi Liu, Xujiang Zhao, Wei Cheng, Runxue Bao, Rui Zhang, Prasenjit Mitra, Haifeng Chen
NAACL, 2024(findings)
paper /
code /
We introduce D-PRUNER, an innovative unstructured dual-pruning method for domain-specific compression on LLM. It is able to extract a compressed, domain-specific, and task-agnostic LLM by identifying weights that are pivotal for both generality and specificity.
|
|
Uncertainty Quantification for In-Context Learning of Large Language Models
Chen Ling,
Xujiang Zhao,
Xuchao Zhang,
Wei Cheng,
Yanchi Liu,
Yiyou Sun,
Mika Oishi,
Takao Osaki,
Katsushi Matsuda,
Jie Ji,
Guangji Bai,
Haifeng Chen,
Liang Zhao,
NAACL, 2024
paper /
code /
We provide an Uncertainty Quantification and Decomposition of In-Context Learning of Large Language Model.
|
|
Open-ended Commonsense Reasoning with Unrestricted Answer Scope
Chen Ling,
Xuchao Zhang,
Xujiang Zhao,
Yanchi Liu,
Wei Cheng,
Mika Oishi,
Takao Osaki,
Katsushi Matsuda,
Haifeng Chen,
Liang Zhao,
EMNLP, 2023 (findings)
paper /
code /
We present an off-the-shelf framework KEEP to predict answers for open-ended commonsense reasoning without requiring answer candidates and a pre-defined answer scope.
|
|
Adaptation Speed Analysis for Fairness-aware Causal Models
Yujie Lin,
Chen Zhao
Minglai Shao,
Xujiang Zhao,
Haifeng Chen,
CIKM, 2023
paper /
code /
This paper aims to explore spurious relationships in structural causal models (SCMs) that arise due to sensitive factors.
|
|
Calibrate Graph Neural Networks under Out-of-Distribution Nodes via Deep Q-learning
Weili Shi,
Xueying Yang
Xujiang Zhao,
Haifeng Chen,
Zhiqiang Tao,
Sheng Li,
CIKM, 2023
paper /
code /
We propose a Graph Edge Re-weighting via Deep Q-learning (GERDQ) framework to calibrate the graph neural networks.
|
|
Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey
Chen Ling,
Xujiang Zhao,
Jiaying Lu,
Chengyuan Deng,
Can Zheng,
Junxiang Wang,
Tanmoy Chowdhury,
Yun Li,
Hejie Cui,
Xuchao Zhang,
Tianyang Zhao,
Amit P.,
Wei Chen,
Haoyu Wang,
Yanchi Liu,
Zhengzhang Chen,
Haifeng Chen,
Chris White,
Quanquan Gu,
Jian Pei,
Carl Yang,
Liang Zhao,
Preprint, 2023
paper /
slides
We present a comprehensive survey on domain specification techniques for large language models, an emerging direction critical for large language model applications. This paper was cited by 2024 Economic Report of the President of the United States
|
|
Multi-Label Temporal Evidential Neural Networks for Early Event Detection
Xujiang Zhao,
Xuchao Zhang,
Chen Zhao,
Jin-hee Cho,
Lance Kaplan,
Dong Hyun Jeong,
Audun Jøsang,
Haifeng Chen,
Feng Chen,
ICASSP, 2023
paper /
code /
slides
We study the problem of early event detection in multi-lable classification, and propose a novel framework, Multi-Label Temporal Evidential Neural Network (MTENN), for multi-label uncertainty estimation in temporal data.
|
|
Knowledge-enhanced Neural Machine Reasoning: A Review
Tanmoy Chowdhury,
Chen Ling,
Xuchao Zhang,
Xujiang Zhao,
Guangji Bai,
Jian Pei,
Haifeng Chen,
Liang Zhao,
Preprint, 2023
paper /
slides
In this survey paper, we provide a comprehensive technical review of the existing knowledge-enhanced reasoning techniques across the diverse range of application domains.
|
|
A Survey on Uncertainty Reasoning and Quantification for Decision Making: Belief Theory Meets Deep Learning
Zhen Guo*,
Zelin Wan*,
Qisheng Zhang*,
Xujiang Zhao*,
Feng Chen,
Jin-hee Cho,
Qi Zhang*,
Lance Kaplan,
Dong Hyun Jeong,
Audun Jøsang,
Information Fusion (Impact IF: 17.5), 2023
paper /
slides
In this survey paper, we study the mature uncertainty research in belief/evidence theories in machine learning/deep learning to tackle complex problems under different types of uncertainty.
|
|
How Out-of-Distribution Data Hurts Semi-Supervised Learning
Xujiang Zhao*,
Krishnateja Killamsetty*,
Rishabh Iyer,
Feng Chen,
ICDM 2022
paper /
code /
slides
We study the key causes about the negative impact of OODs (boundary OODs and faraway ODDs) on SSL and proposed a simple unified robust SSL approach for many existing SSL algorithms in order to improve their robustness against OODs.
|
|
Calibrate Automated Graph Neural Network via Hyperparameter Uncertainty
Xueying Yang
Jiamian Wang,
Xujiang Zhao,
Sheng Li,
Zhiqiang Tao,
CIKM, 2022 (Short paper)
paper /
code /
slides
In this paer, we investigate automated GNN calibration by marrying uncertainty estimation to the hyperparameter optimization (HPO) problem.
|
|
SEED: Sound Event Early Detection via Evidential Uncertainty
Xujiang Zhao,
Xuchao Zhang,
Wei Cheng,
Wenchao Yu,
Yuncong Chen,
Haifeng Chen,
Feng Chen,
ICASSP, 2022
paper /
code /
slides
We propose a novel Polyphonic Evidential Neural Network to model the evidential uncertainty of the class probability with Beta distribution to solve the sound event early detection problem.
|
|
Layer Adaptive Deep Neural Networks for Out-of-distribution Detection
Haoliang Wang,
Chen Zhao,
Xujiang Zhao,
Feng Chen,
PAKDD, 2022
paper /
code /
slides
In this paper, we proposed a novel layer-adaptive OOD detection framework (LA-OOD) for DNNs that can fully utilize the intermediate layers’ outputs.
|
|
RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning
Krishnateja Killamsetty,
Xujiang Zhao,
Rishabh Iyer,
Feng Chen,
NeurIPS, 2021
paper /
code /
slides
We propose a subset selection algorithm in semi-supervised learning to speed up the SSL training. In addition, this algorithm achieve a better performance when unlabeled data consists of Out-of-Distribution (OOD) data and imbalance.
|
|
Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation
Liyan Xu,
Xuchao Zhang,
Xujiang Zhao,
Haifeng Chen,
Feng Chen,
Jinho D. Choi,
EMNLP, 2021 (Short paper, Oral)
paper /
code /
slides
In this work, we propose a self-learning framework that further utilizes unlabeled data of target languages, combined with uncertainty estimation in the process to select high-quality silver labels..
|
|
CLEAR: Contrastive-Prototype Learning with Drift Estimation for Resource Constrained Stream Mining
Zhuoyi Wang,
Chen Zhao,
Yuqiao Chen,
Hemeng Tao,
Yu Lin,
Xujiang Zhao,
Yigong Wang,
Latifur Khan,
WWW, 2021
paper /
code /
slides
CLEAR: Contrastive-Prototype Learning with Drift Estimation for Resource Constrained Stream Mining.
|
|
Multidimensional Uncertainty-Aware Evidential Neural Networks
Yibo Hu,
Yuzhe Ou,
Xujiang Zhao,
Feng Chen,
Jin-hee Cho,
AAAI, 2021
paper /
code /
slides
By considering the multidimensional uncertainty, we proposed a novel uncertainty-aware evidential NN called WGAN-ENN (WENN) for solving an out-of-distribution (OOD) detection problem.
|
|
Uncertainty Aware Semi-Supervised Learning on Graph Data
Xujiang Zhao,
Feng Chen,
Shu Hu,
Jin-hee Cho,
NeurIPS, 2020   (Spotlight)
paper /
code /
slides /
poster /
video
A multi-source uncertainty framework of GNN that reflecting various types of uncertainties in both deep learning and belief/evidence theory domains for node classification predictions.
|
|
Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning
Weishi Shi,
Xujiang Zhao,
Feng Chen,
Qi Yu,
NeurIPS, 2020
paper /
appendix /
code /
slides
A novel multi-source uncertainty prediction approach that enables deep learning models to be actively trained with much less labeled data.
|
|
Uncertainty-Aware Opinion Inference Under Adversarial Attacks
Adil Alim,
Xujiang Zhao,
Jin-hee Cho,
Feng Chen,
Bigdata, 2019
paper /
slides
we propose a highly scalable opinion inference probabilistic model, namely Adversarial Collective Opinion Inference (Adv-COI), which provides a solution to infer unknown opinions with high scalability and robustness under the presence of uncertain,.
|
|
Quantifying Classification Uncertainty using Regularized Evidential Neural Networks
Xujiang Zhao,
Yuzhe Ou,
Lance Kaplan,
Feng Chen,
Jin-hee Cho,
AAAI, 2019 Fall Symposium Series
paper /
code /
slides
This paper presents a new approach, called a regularized EEvidential Neural Networks (ENN), that learns an ENN based on regularizations related to different characteristics of inherent data uncertainty.
|
|
Uncertainty-based Decision Making Using Deep Reinforcement Learning
Xujiang Zhao,
Shu Hu,
Jin-hee Cho,
Feng Chen,
FUSION, 2019
paper /
slides
This paper proposed three DRL-based schemes combining Subjective Logic and deep reinforcement learning where a reward is given based on a different type of uncertainty (i.e., vacuity, dissonance, or monosonance).
|
|
Deep Learning for Predicting Dynamic Uncertain Opinions in Network Data
Xujiang Zhao,
Feng Chen,
Jin-hee Cho,
Bigdata, 2018
paper /
code /
slides
GCN-GRU:Combine Graph Convolutional Network (GCN) and the Gated Recurrent Units (GRU) to model the topological and temporal heterogeneous dependency information of a given dynamic network and conflicting opinions based on robust statistics (uncertainty)
|
|
Deep Learning based Scalable Inference of Uncertain Opinions
Xujiang Zhao,
Feng Chen,
Jin-hee Cho,
ICDM, 2018 (Full paper; Acceptance rate: 8.86%)
paper /
code /
slides /
poster
GCN-VAE-SL: The proposed DL-based opinion inference model handles node-level opinions explicitly in a large-scale network using graph convoluational network (GCN) and variational autoencoder (VAE) techniques.
|
|
Uncertainty-Based Opinion Inference on Network Data Using Graph Convolutional Neural Networks
Xujiang Zhao,
Feng Chen,
Jin-hee Cho,
MILCOM, 2018
paper /
code /
slides
We propose a general framework to model and infer heterogeneous uncertainty information in network data based on GCN and node-level opinions via knowledge distillation.
|
|
Program Committee Member
ICLR 2024, AAAI 2024, KDD 2024, ICML 2024, ACL 2024, COLM2024
ICLR 2023, AAAI 2023, KDD 2023, ICML 2023, NeurIPS 2023
NeurIPS 2022, ICML 2022, KDD 2022, ICLR 2022, WSDM 2022, AAAI 2022, SDM 2022
NeurIPS 2021, KDD 2021
KDD 2020
|
|