Pengfei Li

A sybil attack detection scheme for privacy-preserving mobile social networks

2015

With the pervasiveness of smart phones, mobile social networking (MSN) has received extensive attention in recent years. However, while providing many opportunities to mobile users, MSN also poses new security challenges, and sybil attack is …

Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network

2019 · IEEE Transactions on Neural Networks and Learning Systems

The deep Q-network (DQN) and return-based reinforcement learning are two promising algorithms proposed in recent years. The DQN brings advances to complex sequential decision problems, while return-based algorithms have advantages in making use of sample …

Multi-scaled Topic Embedding for Text Classification

2022

Topic modeling and word embedding are commonly used techniques in natural language processing. However, word embedding lacks discriminating information of homonymy and polysemy as they typically assign a single vector for each word even if …

Anytime-Competitive Reinforcement Learning with Policy Prior

2023 · arXiv (Cornell University)

This paper studies the problem of Anytime-Competitive Markov Decision Process (A-CMDP). Existing works on Constrained Markov Decision Processes (CMDPs) aim to optimize the expected reward while constraining the expected cost over random dynamics, but the …

ChatSchema: A pipeline of extracting structured information with Large Multimodal Models based on schema

2024 · arXiv (Cornell University)

Objective: This study introduces ChatSchema, an effective method for extracting and structuring information from unstructured data in medical paper reports using a combination of Large Multimodal Models (LMMs) and Optical Character Recognition (OCR) based on …