Jungwon Seo

Jungwon Seo, Ferhat Ozgur Catak, Chunming Rong

As privacy concerns and data regulations grow, federated learning (FL) has emerged as a promising approach for training machine learning models across decentralized data sources without sharing raw data. However, a significant challenge in FL is that client data are often non-IID (non-independent and identically distributed), leading to reduced performance compared to centralized learning. While many methods have been proposed to address this issue, their underlying mechanisms are often viewed from different perspectives. Through a comprehensive investigation from gradient descent to FL, and from IID to non-IID data settings, we find that inconsistencies in client loss landscapes primarily cause performance degradation in non-IID scenarios. From this understanding, we observe that existing methods can be grouped into two main strategies: (i) adjusting parameter update paths and (ii) modifying client loss landscapes. These findings offer a clear perspective on addressing non-IID challenges in FL and help guide future research in the field.

Chung Hee Kim, Ka Hei Mak, Jungwon Seo

This paper presents a robotic manipulation technique for dexterous ungrasping. It refers to the capability of securely transferring a grasped object from the gripper to the robot's environment, i.e. the inverse of grasping or picking, through dexterous manipulation. The game of Go offers an example: consider how the player would typically place an initially pinch-grasped stone onto the board through the dexterous interaction between the fingers, the stone, and the board. Likewise, dexterous ungrasping addresses the necessity of changing the object's configuration relative to the gripper or the environment in order to securely keep hold of the object. In particular, we present a planning framework for determining a feasible minimum-cost motion path that completes dexterous ungrasping. Digit asymmetry in a gripper, i.e. difference in digit lengths, is discovered as the key to feasible and secure ungrasping. A set of experiments show the effectiveness of dexterous ungrasping in practical placement tasks.