Author name cluster

Pu-Jen Cheng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

ICLR Conference 2025 Conference Paper

Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification

Hsun-Yu Kuo
Yin-Hsiang Liao
Yu-Chieh Chao
Wei-Yun Ma
Pu-Jen Cheng

Synthetic data augmentation via Large Language Models (LLMs) allows researchers to leverage additional training data, thus enhancing the performance of downstream tasks, especially when real-world data is scarce. However, the generated data can deviate from the real-world data, and this misalignment can bring about deficient results while applying the trained model to applications. Therefore, we proposed efficient weighted-loss approaches to align synthetic data with real-world distribution by emphasizing high-quality and diversified data generated by LLMs using merely a tiny amount of real-world data. We empirically assessed the effectiveness of our methods on multiple text classification tasks, and the results showed that leveraging our approaches on a BERT-level model robustly outperformed standard cross-entropy and other data weighting approaches, providing potential solutions to effectively leveraging synthetic data from any suitable data generator.

Details

ICML Conference 2023 Conference Paper

Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs

Guan-Ting Liu
En-Pei Hu
Pu-Jen Cheng
Hung-yi Lee
Shao-Hua Sun

Aiming to produce reinforcement learning (RL) policies that are human-interpretable and can generalize better to novel scenarios, Trivedi et al. (2021) present a method (LEAPS) that first learns a program embedding space to continuously parameterize diverse programs from a pre-generated program dataset, and then searches for a task-solving program in the learned program embedding space when given a task. Despite the encouraging results, the program policies that LEAPS can produce are limited by the distribution of the program dataset. Furthermore, during searching, LEAPS evaluates each candidate program solely based on its return, failing to precisely reward correct parts of programs and penalize incorrect parts. To address these issues, we propose to learn a meta-policy that composes a series of programs sampled from the learned program embedding space. By learning to compose programs, our proposed hierarchical programmatic reinforcement learning (HPRL) framework can produce program policies that describe out-of-distributionally complex behaviors and directly assign credits to programs that induce desired behaviors. The experimental results in the Karel domain show that our proposed framework outperforms baselines. The ablation studies confirm the limitations of LEAPS and justify our design choices.

Details

AAMAS Conference 2022 Conference Paper

Improving Generalization with Cross-State Behavior Matching in Deep Reinforcement Learning

Guan-Ting Liu
Guan-Yu Lin
Pu-Jen Cheng

Representation learning on visualized input is an essential yet challenging task for deep reinforcement learning (RL). To help the RL agent learn more general and discriminative representation among various states, we present cross-state self-constraint (CSSC). This novel technique regularizes representation learning by comparing state embedding similarities across different state-action pairs. We test our proposed method on the OpenAI Procgen benchmark with Rainbow and PPO and demonstrate significant improvement across most Procgen environments.

PDF

IS Journal 2016 Journal Article

An Efficient Multiple Session Key Establishment Scheme for VANET Group Integration

Cheng-Chi Lee
Yan-Ming Lai
Pu-Jen Cheng

VANET (vehicular ad hoc network) is used to create communication networks for vehicles or other roadside devices so that they can quickly share and receive messages. However, VANET belongs to a family of wireless networks, which means that its functions are unsafe. To provide safe communication channels, key-agreements technology can be introduced to VANET communication. Traditional key-agreement schemes, however, are inefficient and consume too many resources, especially when handling large or combined groups of users. To improve efficiency, the Chinese remainder theorem is used to build a batch key-agreement protocol. The improved key for VANET environments is a safer and quicker way to establish communication channels.

Details DOI