Welcome to my homepage!

E-mail: lixuwang2025@u.northwestern.edu

Address: L476, Technological Institute, 2145 Sheridan Road, Evanston, IL, USA

Google Scholar, LinkedIn, GitHub

This is Lixu Wang. I am a Ph.D. candidate in Computer Science at Northwestern University (NU) starting in Spring 2021, advised by Prof. Qi Zhu and Prof. Xiao Wang, and partially supported by IBM PhD Fellowship. Prior to Northwestern, I obtained my B.E. from Zhejiang University (ZJU) in July 2020 under the supervision of Prof. Wenyuan Xu.  I am open to all kinds of collaboration, please drop me an email if you are interested in my research.

Recent News

Research Interest

I aim to create socially responsible machine learning (ML) models, i.e., ML models that can protect the privacy of their training data and minimize the chance of being misused. In particular, to ensure privacy protection, those models must be resistant to various privacy attacks. To prevent harmful social impacts from the misuse of ML models, their generalization ability on unintentional data domains and tasks must be reduced. To achieve these goals, I have been developing novel ML models and tools with a diverse set of techniques in Optimization Theory, Information Theory, and Cryptography. Greater ability comes with greater responsibility, and this applies equally to ML technology. ML models with social responsibility can protect data privacy and prevent serious consequences caused by the harmful use of models, such as teenagers obtaining violent information from recommendation systems or criminals using ML models to engage in criminal activities.

In particular, my current research lies in: 

Selected Publications ( * denotes equal contribution, ** denotes alphabetical order, # denotes corresponding authors)

Federated Learning with New Knowledge: Fundamentals, Advances, and Futures

Phase-driven Domain Generalizable Learning for Nonstationary Time Series

Federated Continual Novel Class Learning 

DACR: Distribution-Augmented Contrastive Reconstruction for Time-Series Anomaly Detection 

Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand

PolicyCleanse: Detecting and Mitigating Trojan Attacks in Reinforcement Learning 

Deja Vu: Continual Model Generalization for Unseen Domains 

Federated Class Incremental Learning 

Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization 

Weak Adaptation Learning - Addressing Cross-domain Data Insufficiency with Weak Annotator

Addressing Class Imbalance in Federated Learning, 

mID: Tracing Screen Photos via Moiré Patterns

InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation

Services