liyan2015
Data ScientistMember since June 24, 2026
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
SHE-LoRA
February 12, 2026 – Present
SHE-LoRA: a selective homomorphic encryption framework that enables efficient, privacy-preserving federated fine-tuning of LLMs. By encrypting only the most sensitive LoRA parameters via CKKS, SHE-LoRA reduces communication overhead by ~99.71% and encryption time by ~99.87%, while maintaining model performance and strong resistance to attacks.
View ProjectP3Forecast
March 20, 2025 – July 27, 2025
a Personalized Privacy Preserving cloud workload prediction framework based on Federated Generative Adversarial Networks (GANs), which allows cloud providers with Non-IID workload data to collaboratively train workload prediction models as preferred while protecting privacy.
View Projectadma2025-trustworthy-data-mining
March 18, 2025 – June 4, 2025
adma2025-trustworthy-data-mining — GitHub repository
View ProjectAdapLDP-FL
January 21, 2025 – May 24, 2025
An Adaptive Local Difference Privacy FL (AdapLDP-FL) scheme to optimally balance client-side privacy preservation and model performance via noise scaling and model update direction correction.
View ProjectJC-workload-predictor
October 14, 2023 – December 19, 2025
JC-workload-predictor — GitHub repository
View ProjectAdaptiveBatchHE
October 6, 2023 – March 21, 2025
An adaptive batch homomorphic encryption framework for cross-device Federated Learning, which determines cost-efficient and sufficiently secure encryption strategies for clients with heterogeneous data and system capabilities.
View ProjectSUMO-RL-MobiCharger
June 13, 2023 – March 16, 2025
OpenAI-gym-like Reinforcement Learning environment for Dispatching of Mobile Chargers with SUMO. Compatible with Gym and popular RL libraries such as stable-baselines3.
View ProjectCultural Fit Analysis
The candidate's projects are primarily academic/research-oriented and personal, indicating a strong drive for technical exploration and problem-solving. However, the lack of diverse project types (e.g., team-based, production-focused) and limited information on collaboration might suggest a need to assess their fit within a more structured team environment. The projects align well with a Data Scientist role, particularly one focused on advanced ML/privacy research.
Soft Skills & Operational Fit
Insufficient data to assess soft skills or operational fit. The candidate's project descriptions indicate a focus on complex technical challenges, suggesting strong problem-solving abilities, but collaboration and communication aspects are not evaluated.