64 citations · 358 across the 46 of their papers we have counts for
28 papers · 1 filter
Rethinking Personalized Reward Modeling for LLMs under Preference Heterogeneity via Group-Debiased Federated Learning
Seongyoon Kim, Boryeong Cho, Jihwan Oh +2
Large language models are increasingly aligned to human preferences via reward modeling, but user preference data are sensitive and often cannot be centralized. Federated learning…
FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning
Gihun Lee, Minchan Jeong, Sangmook Kim +2
Federated Learning (FL) aggregates locally trained models from individual clients to construct a global model. While FL enables learning a model with data privacy, it often suffers…
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning
Hojoon Lee, Hanseul Cho, Hyunseung Kim +5
In Reinforcement Learning (RL), enhancing sample efficiency is crucial, particularly in scenarios when data acquisition is costly and risky. In principle, off-policy RL algorithms…
Toward Risk-based Optimistic Exploration for Cooperative Multi-Agent Reinforcement Learning
Jihwan Oh, Joonkee Kim, Minchan Jeong +1
The multi-agent setting is intricate and unpredictable since the behaviors of multiple agents influence one another. To address this environmental uncertainty, distributional reinf…
Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks
Junghyun Lee, Laura Schmid, Se-Young Yun
Multi-armed bandits are extensively used to model sequential decision-making, making them ubiquitous in many real-life applications such as online recommender systems and wireless…
Denoising after Entropy-based Debiasing A Robust Training Method for Dataset Bias with Noisy Labels
Sumyeong Ahn, Se-Young Yun
Improperly constructed datasets can result in inaccurate inferences. For instance, models trained on biased datasets perform poorly in terms of generalization (i.e., dataset bias).…
Nearly Optimal Latent State Decoding in Block MDPs
Yassir Jedra, Junghyun Lee, Alexandre Proutière +1
We investigate the problems of model estimation and reward-free learning in episodic Block MDPs. In these MDPs, the decision maker has access to rich observations or contexts gener…
The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions
Mingyu Kim, Jihwan Oh, Yongsik Lee +4
In this paper, we propose a novel benchmark called the StarCraft Multi-Agent Challenges+, where agents learn to perform multi-stage tasks and to use environmental factors without p…
Risk Perspective Exploration in Distributional Reinforcement Learning
Jihwan Oh, Joonkee Kim, Se-Young Yun
Distributional reinforcement learning demonstrates state-of-the-art performance in continuous and discrete control settings with the features of variance and risk, which can be use…
Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Search
Taehyeon Kim, Heesoo Myeong, Se-Young Yun
Knowledge Distillation (KD) has recently emerged as a popular method for compressing neural networks. In recent studies, generalized distillation methods that find parameters and a…
Demystifying the Base and Novel Performances for Few-shot Class-incremental Learning
Jaehoon Oh, Se-Young Yun
Few-shot class-incremental learning (FSCIL) has addressed challenging real-world scenarios where unseen novel classes continually arrive with few samples. In these scenarios, it is…
Benchmark Dataset for Precipitation Forecasting by Post-Processing the Numerical Weather Prediction
Taehyeon Kim, Namgyu Ho, Donggyu Kim +1
Precipitation forecasting is an important scientific challenge that has wide-reaching impacts on society. Historically, this challenge has been tackled using numerical weather pred…
A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise
Jongwoo Ko, Bongsoo Yi, Se-Young Yun
As deep neural networks can easily overfit noisy labels, robust training in the presence of noisy labels is becoming an important challenge in modern deep learning. While existing…
Supernet Training for Federated Image Classification under System Heterogeneity
Taehyeon Kim, Se-Young Yun
Efficient deployment of deep neural networks across many devices and resource constraints, particularly on edge devices, is one of the most challenging problems in the presence of…
Mitigating Dataset Bias by Using Per-sample Gradient
Sumyeong Ahn, Seongyoon Kim, Se-young Yun
The performance of deep neural networks is strongly influenced by the training dataset setup. In particular, when attributes having a strong correlation with the target attribute a…
Adversarial Bandits against Arbitrary Strategies
Jung-hun Kim, Se-Young Yun
We study the adversarial bandit problem against arbitrary strategies, where the difficulty is captured by an unknown parameter , which is the number of switches in the best arm…
How to Fine-tune Models with Few Samples: Update, Data Augmentation, and Test-time Augmentation
Yujin Kim, Jaehoon Oh, Sungnyun Kim +1
Most of the recent few-shot learning (FSL) algorithms are based on transfer learning, where a model is pre-trained using a large amount of source data, and the pre-trained model is…
FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learning
SangMook Kim, Wonyoung Shin, Soohyuk Jang +2
Robustness is becoming another important challenge of federated learning in that the data collection process in each client is naturally accompanied by noisy labels. However, it is…
Neural Processes with Stochastic Attention: Paying more attention to the context dataset
Mingyu Kim, Kyeongryeol Go, Se-Young Yun
Neural processes (NPs) aim to stochastically complete unseen data points based on a given context dataset. NPs essentially leverage a given dataset as a context representation to d…
Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty
Jaehoon Oh, Sungnyun Kim, Namgyu Ho +3
Cross-domain few-shot learning (CD-FSL) has drawn increasing attention for handling large differences between the source and target domains--an important concern in real-world scen…
Rotting Infinitely Many-armed Bandits
Jung-hun Kim, Milan Vojnovic, Se-Young Yun
We consider the infinitely many-armed bandit problem with rotting rewards, where the mean reward of an arm decreases at each pull of the arm according to an arbitrary trend with ma…
Self-Contrastive Learning: Single-viewed Supervised Contrastive Framework using Sub-network
Sangmin Bae, Sungnyun Kim, Jongwoo Ko +3
Contrastive loss has significantly improved performance in supervised classification tasks by using a multi-viewed framework that leverages augmentation and label information. The…
FedBABU: Towards Enhanced Representation for Federated Image Classification
Jaehoon Oh, Sangmook Kim, Se-Young Yun
Federated learning has evolved to improve a single global model under data heterogeneity (as a curse) or to develop multiple personalized models using data heterogeneity (as a bles…
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
Gihun Lee, Minchan Jeong, Yongjin Shin +2
In federated learning, a strong global model is collaboratively learned by aggregating clients' locally trained models. Although this precludes the need to access clients' data dir…