54 citations · 81 across the 12 of their papers we have counts for
12 papers
Unlocking the Potential of Model Calibration in Federated Learning
Yun-Wei Chu, Dong-Jun Han, Seyyedali Hosseinalipour +1
Over the past several years, various federated learning (FL) methodologies have been developed to improve model accuracy, a primary performance metric in machine learning. However,…
Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks
Yun-Wei Chu, Dong-Jun Han, Seyyedali Hosseinalipour +1
A few recent studies have demonstrated that leveraging centrally pre-trained models can offer advantageous initializations for federated learning (FL). However, existing pre-traini…
Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation
Yun-Wei Chu, Dong-Jun Han, Christopher G. Brinton
Federated learning (FL) is a promising distributed machine learning paradigm that enables multiple clients to collaboratively train a global model. In this paper, we focus on a pra…
Connectivity-Aware Semi-Decentralized Federated Learning over Time-Varying D2D Networks
Rohit Parasnis, Seyyedali Hosseinalipour, Yun-Wei Chu +2
Semi-decentralized federated learning blends the conventional device to-server (D2S) interaction structure of federated model training with localized device-to-device (D2D) communi…
Multi-Layer Personalized Federated Learning for Mitigating Biases in Student Predictive Analytics
Yun-Wei Chu, Seyyedali Hosseinalipour, Elizabeth Tenorio +4
Conventional methods for student modeling, which involve predicting grades based on measured activities, struggle to provide accurate results for minority/underrepresented student…
Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning
Yun-Wei Chu, Seyyedali Hosseinalipour, Elizabeth Tenorio +4
Traditional learning-based approaches to student modeling generalize poorly to underrepresented student groups due to biases in data availability. In this paper, we propose a metho…
Let's Talk! Striking Up Conversations via Conversational Visual Question Generation
Shih-Han Chan, Tsai-Lun Yang, Yun-Wei Chu +4
An engaging and provocative question can open up a great conversation. In this work, we explore a novel scenario: a conversation agent views a set of the user's photos (for example…
Click-Based Student Performance Prediction: A Clustering Guided Meta-Learning Approach
Yun-Wei Chu, Elizabeth Tenorio, Laura Cruz +3
We study the problem of predicting student knowledge acquisition in online courses from clickstream behavior. Motivated by the proliferation of eLearning lecture delivery, we speci…
Plot and Rework: Modeling Storylines for Visual Storytelling
Chi-Yang Hsu, Yun-Wei Chu, Ting-Hao 'Kenneth' Huang +1
Writing a coherent and engaging story is not easy. Creative writers use their knowledge and worldview to put disjointed elements together to form a coherent storyline, and work and…
MVIN: Learning Multiview Items for Recommendation
Chang-You Tai, Meng-Ru Wu, Yun-Wei Chu +2
Researchers have begun to utilize heterogeneous knowledge graphs (KGs) as auxiliary information in recommendation systems to mitigate the cold start and sparsity issues. However, u…
Multi-step Joint-Modality Attention Network for Scene-Aware Dialogue System
Yun-Wei Chu, Kuan-Yen Lin, Chao-Chun Hsu +1
Understanding dynamic scenes and dialogue contexts in order to converse with users has been challenging for multimodal dialogue systems. The 8-th Dialog System Technology Challenge…
GraphSW: a training protocol based on stage-wise training for GNN-based Recommender Model
Chang-You Tai, Meng-Ru Wu, Yun-Wei Chu +1
Recently, researchers utilize Knowledge Graph (KG) as side information in recommendation system to address cold start and sparsity issue and improve the recommendation performance.…