Search Results for author: Se-Young Yun

Found 80 papers, 46 papers with code

Preservation of the Global Knowledge by Not-True Distillation in Federated Learning

2 code implementations6 Jun 2021 Gihun Lee, Minchan Jeong, Yongjin Shin, Sangmin Bae, Se-Young Yun

In federated learning, a strong global model is collaboratively learned by aggregating clients' locally trained models.

Continual Learning Federated Learning +1

FedBABU: Towards Enhanced Representation for Federated Image Classification

3 code implementations4 Jun 2021 Jaehoon Oh, Sangmook Kim, Se-Young Yun

Based on this observation, we propose a novel federated learning algorithm, coined FedBABU, which only updates the body of the model during federated training (i. e., the head is randomly initialized and never updated), and the head is fine-tuned for personalization during the evaluation process.

Classification Federated Learning +1

FedBABU: Toward Enhanced Representation for Federated Image Classification

1 code implementation ICLR 2022 Jaehoon Oh, Sangmook Kim, Se-Young Yun

Based on this observation, we propose a novel federated learning algorithm, coined FedBABU, which only updates the body of the model during federated training (i. e., the head is randomly initialized and never updated), and the head is fine-tuned for personalization during the evaluation process.

Classification Federated Learning +1

Large Language Models Are Reasoning Teachers

1 code implementation20 Dec 2022 Namgyu Ho, Laura Schmid, Se-Young Yun

We evaluate our method on a wide range of public models and complex tasks.

DistiLLM: Towards Streamlined Distillation for Large Language Models

2 code implementations6 Feb 2024 Jongwoo Ko, Sungnyun Kim, Tianyi Chen, Se-Young Yun

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities.

Instruction Following Knowledge Distillation

MixCo: Mix-up Contrastive Learning for Visual Representation

1 code implementation13 Oct 2020 Sungnyun Kim, Gihun Lee, Sangmin Bae, Se-Young Yun

Contrastive learning has shown remarkable results in recent self-supervised approaches for visual representation.

Contrastive Learning Self-Supervised Learning

Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation

1 code implementation19 May 2021 Taehyeon Kim, Jaehoon Oh, Nakyil Kim, Sangwook Cho, Se-Young Yun

From this observation, we consider an intuitive KD loss function, the mean squared error (MSE) between the logit vectors, so that the student model can directly learn the logit of the teacher model.

Knowledge Distillation Learning with noisy labels

BOIL: Towards Representation Change for Few-shot Learning

1 code implementation ICLR 2021 Jaehoon Oh, Hyungjun Yoo, ChangHwan Kim, Se-Young Yun

It has recently been hypothesized that representation reuse, which makes little change in efficient representations, is the dominant factor in the performance of the meta-initialized model through MAML in contrast to representation change, which causes a significant change in representations.

Few-Shot Learning

FINE Samples for Learning with Noisy Labels

1 code implementation NeurIPS 2021 Taehyeon Kim, Jongwoo Ko, Sangwook Cho, Jinhwan Choi, Se-Young Yun

Our framework, coined as filtering noisy instances via their eigenvectors (FINE), provides a robust detector with derivative-free simple methods having theoretical guarantees.

General Classification Learning with noisy labels

Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding

1 code implementation9 Oct 2023 Sangmin Bae, Jongwoo Ko, Hwanjun Song, Se-Young Yun

To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation paths for each token based on the complexity of generating the subsequent token.

Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation

1 code implementation19 May 2023 Kangwook Jang, Sungnyun Kim, Se-Young Yun, Hoirin Kim

Transformer-based speech self-supervised learning (SSL) models, such as HuBERT, show surprising performance in various speech processing tasks.

Self-Supervised Learning

Re-thinking Federated Active Learning based on Inter-class Diversity

1 code implementation CVPR 2023 Sangmook Kim, Sangmin Bae, Hwanjun Song, Se-Young Yun

In this work, we first demonstrate that the superiority of two selector models depends on the global and local inter-class diversity.

Active Learning Federated Learning

Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty

2 code implementations1 Feb 2022 Jaehoon Oh, Sungnyun Kim, Namgyu Ho, Jin-Hwa Kim, Hwanjun Song, Se-Young Yun

This data enables self-supervised pre-training on the target domain, in addition to supervised pre-training on the source domain.

cross-domain few-shot learning

The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions

1 code implementation5 Jul 2022 Mingyu Kim, Jihwan Oh, Yongsik Lee, Joonkee Kim, SeongHwan Kim, Song Chong, Se-Young Yun

This challenge, on the other hand, is interested in the exploration capability of MARL algorithms to efficiently learn implicit multi-stage tasks and environmental factors as well as micro-control.

SMAC+

Benchmark Dataset for Precipitation Forecasting by Post-Processing the Numerical Weather Prediction

1 code implementation30 Jun 2022 Taehyeon Kim, Namgyu Ho, Donggyu Kim, Se-Young Yun

Historically, this challenge has been tackled using numerical weather prediction (NWP) models, grounded on physics-based simulations.

Computational Efficiency Precipitation Forecasting

Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning

1 code implementation CVPR 2023 Sungnyun Kim, Sangmin Bae, Se-Young Yun

Fortunately, the recent self-supervised learning (SSL) is a promising approach to pretrain a model without annotations, serving as an effective initialization for any downstream tasks.

Representation Learning Self-Supervised Learning

SIPA: A Simple Framework for Efficient Networks

1 code implementation24 Apr 2020 Gihun Lee, Sangmin Bae, Jaehoon Oh, Se-Young Yun

With the success of deep learning in various fields and the advent of numerous Internet of Things (IoT) devices, it is essential to lighten models suitable for low-power devices.

Math

Self-Contrastive Learning: Single-viewed Supervised Contrastive Framework using Sub-network

1 code implementation29 Jun 2021 Sangmin Bae, Sungnyun Kim, Jongwoo Ko, Gihun Lee, Seungjong Noh, Se-Young Yun

To this end, we propose Self-Contrastive (SelfCon) learning, which self-contrasts within multiple outputs from the different levels of a single network.

Contrastive Learning

CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition

1 code implementation10 Feb 2023 Sumyeong Ahn, Jongwoo Ko, Se-Young Yun

To handle this restriction, several methods have been developed that increase the representations of minority samples by leveraging the features of the majority samples.

Data Augmentation Long-tail Learning

HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning

1 code implementation1 Nov 2023 Yongjin Yang, Joonkee Kim, Yujin Kim, Namgyu Ho, James Thorne, Se-Young Yun

With the proliferation of social media, accurate detection of hate speech has become critical to ensure safety online.

Hate Speech Detection

Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions

1 code implementation1 Nov 2023 Taehyeon Kim, Joonkee Kim, Gihun Lee, Se-Young Yun

Notably, utilizing 'opposite' as the noisy instruction in ID, which exhibits the maximum divergence from the original instruction, consistently produces the most significant performance gains across multiple models and tasks.

Few-Shot NLI Instruction Following +2

NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models

1 code implementation16 Oct 2023 Jongwoo Ko, Seungjoon Park, Yujin Kim, Sumyeong Ahn, Du-Seong Chang, Euijai Ahn, Se-Young Yun

Structured pruning methods have proven effective in reducing the model size and accelerating inference speed in various network architectures such as Transformers.

A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise

1 code implementation15 Jun 2022 Jongwoo Ko, Bongsoo Yi, Se-Young Yun

While existing methods address this problem in various directions, they still produce unpredictable sub-optimal results since they rely on the posterior information estimated by the feature extractor corrupted by noisy labels.

FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learning

1 code implementation3 May 2022 Sangmook Kim, Wonyoung Shin, Soohyuk Jang, Hwanjun Song, Se-Young Yun

Robustness is becoming another important challenge of federated learning in that the data collection process in each client is naturally accompanied by noisy labels.

Federated Learning

Region-Conditioned Orthogonal 3D U-Net for Weather4Cast Competition

2 code implementations5 Dec 2022 Taehyeon Kim, Shinhwan Kang, Hyeonjeong Shin, Deukryeol Yoon, Seongha Eom, Kijung Shin, Se-Young Yun

The Weather4Cast competition (hosted by NeurIPS 2022) required competitors to predict super-resolution rain movies in various regions of Europe when low-resolution satellite contexts covering wider regions are given.

Data Augmentation Super-Resolution

Mitigating Dataset Bias by Using Per-sample Gradient

1 code implementation31 May 2022 Sumyeong Ahn, Seongyoon Kim, Se-Young Yun

In this study, we propose a debiasing algorithm, called PGD (Per-sample Gradient-based Debiasing), that comprises three steps: (1) training a model on uniform batch sampling, (2) setting the importance of each sample in proportion to the norm of the sample gradient, and (3) training the model using importance-batch sampling, whose probability is obtained in step (2).

Attribute

Revisiting Orthogonality Regularization: A Study for Convolutional Neural Networks in Image Classification

1 code implementation IEEE Access 2022 Taehyeon Kim, Se-Young Yun

Recent research in deep Convolutional Neural Networks(CNN) faces the challenges of vanishing/exploding gradient issues, training instability, and feature redundancy.

Image Classification

Improving Adaptability and Generalizability of Efficient Transfer Learning for Vision-Language Models

1 code implementation27 Nov 2023 Yongjin Yang, Jongwoo Ko, Se-Young Yun

Vision-Language Models (VLMs) like CLIP have demonstrated remarkable applicability across a variety of downstream tasks, including zero-shot image classification.

General Knowledge Image Classification +2

Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning

1 code implementation18 Dec 2023 Yongjin Yang, Taehyeon Kim, Se-Young Yun

Second, to address the pitfalls of noisy statistics, we deploy two strategies: a progressive training of the two adapters and an adaptive distillation technique derived from features determined by the model solely with the adapter devoid of a normalization layer.

cross-domain few-shot learning

Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning

1 code implementation13 Feb 2024 Haeju Lee, Minchan Jeong, Se-Young Yun, Kee-Eung Kim

We argue that when we extract knowledge from source tasks via training source prompts, we need to consider this correlation among source tasks for better transfer to target tasks.

Transfer Learning

Robust Streaming PCA

1 code implementation8 Feb 2019 Daniel Bienstock, Minchan Jeong, Apurv Shukla, Se-Young Yun

We consider streaming principal component analysis when the stochastic data-generating model is subject to perturbations.

Supernet Training for Federated Image Classification under System Heterogeneity

1 code implementation3 Jun 2022 Taehyeon Kim, Se-Young Yun

The approach is inspired by observing that averaging parameters during model aggregation for FL is similar to weight-sharing in supernet training.

Classification Federated Learning +2

Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks

1 code implementation18 Oct 2022 Jaehoon Oh, Jongwoo Ko, Se-Young Yun

Translation has played a crucial role in improving the performance on multilingual tasks: (1) to generate the target language data from the source language data for training and (2) to generate the source language data from the target language data for inference.

Sentence Sentence Classification +1

Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks

1 code implementation9 Mar 2023 Junghyun Lee, Laura Schmid, Se-Young Yun

Then, to mitigate the issue of high communication costs incurred by flooding in complex networks, we propose a new protocol called Flooding with Absorption (FwA).

Decision Making Multi-Armed Bandits +1

Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion

1 code implementation28 Oct 2023 Junghyun Lee, Se-Young Yun, Kwang-Sung Jun

Logistic bandit is a ubiquitous framework of modeling users' choices, e. g., click vs. no click for advertisement recommender system.

Recommendation Systems

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

1 code implementation NeurIPS 2023 Junghyun Lee, Hanseul Cho, Se-Young Yun, Chulhee Yun

Fair Principal Component Analysis (PCA) is a problem setting where we aim to perform PCA while making the resulting representation fair in that the projected distributions, conditional on the sensitive attributes, match one another.

Optimal Cluster Recovery in the Labeled Stochastic Block Model

no code implementations NeurIPS 2016 Se-Young Yun, Alexandre Proutiere

We find the set of parameters such that there exists a clustering algorithm with at most $s$ misclassified items in average under the general LSBM and for any $s=o(n)$, which solves one open problem raised in \cite{abbe2015community}.

Clustering Community Detection +1

Streaming, Memory Limited Matrix Completion with Noise

no code implementations13 Apr 2015 Se-Young Yun, Marc Lelarge, Alexandre Proutiere

We propose a streaming algorithm which produces an estimate of the original matrix with a vanishing mean square error, uses memory space scaling linearly with the ambient dimension of the matrix, i. e. the memory required to store the output alone, and spends computations as much as the number of non-zero entries of the input matrix.

Matrix Completion

Spectrogram-channels u-net: a source separation model viewing each channel as the spectrogram of each source

no code implementations26 Oct 2018 Jaehoon Oh, Duyeon Kim, Se-Young Yun

The proposed model can be used for not only singing voice separation but also multi-instrument separation by changing only the number of output channels.

Information Retrieval Music Information Retrieval +3

Fast and Memory Optimal Low-Rank Matrix Approximation

no code implementations NeurIPS 2015 Se-Young Yun, Marc Lelarge, Alexandre Proutiere

This means that its average mean-square error converges to 0 as $m$ and $n$ grow large (i. e., $\|\hat{M}^{(k)}-M^{(k)} \|_F^2 = o(mn)$ with high probability, where $\hat{M}^{(k)}$ and $M^{(k)}$ denote the output of SLA and the optimal rank $k$ approximation of $M$, respectively).

Streaming, Memory Limited Algorithms for Community Detection

no code implementations NeurIPS 2014 Se-Young Yun, Marc Lelarge, Alexandre Proutiere

The first algorithm is {\it offline}, as it needs to store and keep the assignments of nodes to clusters, and requires a memory that scales linearly with the network size.

Clustering Community Detection

Accelerated MM Algorithms for Ranking Scores Inference from Comparison Data

1 code implementation1 Jan 2019 Milan Vojnovic, Se-Young Yun, Kaifang Zhou

In this paper, we study a popular method for inference of the Bradley-Terry model parameters, namely the MM algorithm, for maximum likelihood estimation and maximum a posteriori probability estimation.

Bayesian Inference

Spectral Approximate Inference

no code implementations14 May 2019 Sejun Park, Eunho Yang, Se-Young Yun, Jinwoo Shin

Our contribution is two-fold: (a) we first propose a fully polynomial-time approximation scheme (FPTAS) for approximating the partition function of GM associating with a low-rank coupling matrix; (b) for general high-rank GMs, we design a spectral mean-field scheme utilizing (a) as a subroutine, where it approximates a high-rank GM into a product of rank-1 GMs for an efficient approximation of the partition function.

Accurate Community Detection in the Stochastic Block Model via Spectral Algorithms

no code implementations23 Dec 2014 Se-Young Yun, Alexandre Proutiere

We consider the problem of community detection in the Stochastic Block Model with a finite number $K$ of communities of sizes linearly growing with the network size $n$.

Social and Information Networks Data Structures and Algorithms

Reinforcement with Fading Memories

no code implementations29 Jul 2019 Kuang Xu, Se-Young Yun

We focus on a family of decision rules where the agent makes a new choice by randomly selecting an action with a probability approximately proportional to the amount of past rewards associated with each action in her memory.

Decision Making

Understanding Knowledge Distillation

no code implementations1 Jan 2021 Taehyeon Kim, Jaehoon Oh, Nakyil Kim, Sangwook Cho, Se-Young Yun

To verify this conjecture, we test an extreme logit learning model, where the KD is implemented with Mean Squared Error (MSE) between the student's logit and the teacher's logit.

Knowledge Distillation

Task Calibration for Distributional Uncertainty in Few-Shot Classification

no code implementations1 Jan 2021 Sungnyun Kim, Se-Young Yun

As numerous meta-learning algorithms improve performance when solving few-shot classification problems for practical applications, accurate prediction of uncertainty, though challenging, has been considered essential.

Classification General Classification +1

Regret in Online Recommendation Systems

no code implementations NeurIPS 2020 Kaito Ariu, Narae Ryu, Se-Young Yun, Alexandre Proutière

Interestingly, our analysis reveals the relative weights of the different components of regret: the component due to the constraint of not presenting the same item twice to the same user, that due to learning the chances users like items, and finally that arising when learning the underlying structure.

Recommendation Systems

TornadoAggregate: Accurate and Scalable Federated Learning via the Ring-Based Architecture

no code implementations6 Dec 2020 Jin-woo Lee, Jaehoon Oh, Sungsu Lim, Se-Young Yun, Jae-Gil Lee

Federated learning has emerged as a new paradigm of collaborative machine learning; however, many prior studies have used global aggregation along a star topology without much consideration of the communication scalability or the diurnal property relied on clients' local time variety.

Federated Learning

Test Score Algorithms for Budgeted Stochastic Utility Maximization

1 code implementation30 Dec 2020 Dabeen Lee, Milan Vojnovic, Se-Young Yun

Motivated by recent developments in designing algorithms based on individual item scores for solving utility maximization problems, we study the framework of using test scores, defined as a statistic of observed individual item performance data, for solving the budgeted stochastic utility maximization problem.

Mitigating Dataset Bias Using Per-Sample Gradients From A Biased Classifier

no code implementations29 Sep 2021 Sumyeong Ahn, Se-Young Yun

The performance of deep neural networks (DNNs) primarily depends on the configuration of the training set.

Self-Contrastive Learning

no code implementations29 Sep 2021 Sangmin Bae, Sungnyun Kim, Jongwoo Ko, Gihun Lee, Seungjong Noh, Se-Young Yun

This paper proposes a novel contrastive learning framework, called Self-Contrastive (SelfCon) Learning, that self-contrasts within multiple outputs from the different levels of a multi-exit network.

Contrastive Learning

Rotting Infinitely Many-armed Bandits

1 code implementation31 Jan 2022 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 maximum rotting rate $\varrho=o(1)$.

ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning

no code implementations11 May 2022 Jaehoon Oh, Sungnyun Kim, Namgyu Ho, Jin-Hwa Kim, Hwanjun Song, Se-Young Yun

Cross-domain few-shot learning (CD-FSL), where there are few target samples under extreme differences between source and target domains, has recently attracted huge attention.

cross-domain few-shot learning Transfer Learning

How to Fine-tune Models with Few Samples: Update, Data Augmentation, and Test-time Augmentation

no code implementations13 May 2022 Yujin Kim, Jaehoon Oh, Sungnyun Kim, Se-Young Yun

Next, we show that data augmentation cannot guarantee few-shot performance improvement and investigate the effectiveness of data augmentation based on the intensity of augmentation.

Data Augmentation Few-Shot Learning +1

Adversarial Bandits against Arbitrary Strategies

no code implementations30 May 2022 Jung-hun Kim, Se-Young Yun

We study the adversarial bandit problem against arbitrary strategies, in which $S$ is the parameter for the hardness of the problem and this parameter is not given to the agent.

Demystifying the Base and Novel Performances for Few-shot Class-incremental Learning

no code implementations18 Jun 2022 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.

Few-Shot Class-Incremental Learning Incremental Learning

Risk Perspective Exploration in Distributional Reinforcement Learning

no code implementations28 Jun 2022 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 used to explore.

Distributional Reinforcement Learning reinforcement-learning +2

Nearly Optimal Latent State Decoding in Block MDPs

1 code implementation17 Aug 2022 Yassir Jedra, Junghyun Lee, Alexandre Proutière, Se-Young Yun

We investigate the problems of model estimation and reward-free learning in episodic Block MDPs.

Denoising after Entropy-based Debiasing A Robust Training Method for Dataset Bias with Noisy Labels

no code implementations1 Dec 2022 Sumyeong Ahn, Se-Young Yun

Furthermore, we find that running denoising algorithms before debiasing is ineffective because denoising algorithms reduce the impact of difficult-to-learn samples, including valuable bias-conflicting samples.

Denoising

Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective

1 code implementation3 Feb 2023 Jongwoo Ko, Seungjoon Park, Minchan Jeong, Sukjin Hong, Euijai Ahn, Du-Seong Chang, Se-Young Yun

Knowledge distillation (KD) is a highly promising method for mitigating the computational problems of pre-trained language models (PLMs).

Knowledge Distillation

Toward Risk-based Optimistic Exploration for Cooperative Multi-Agent Reinforcement Learning

no code implementations3 Mar 2023 Jihwan Oh, Joonkee Kim, Minchan Jeong, Se-Young Yun

In this paper, we present a risk-based exploration that leads to collaboratively optimistic behavior by shifting the sampling region of distribution.

Distributional Reinforcement Learning Multi-agent Reinforcement Learning +2

Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model

no code implementations18 Jun 2023 Kaito Ariu, Alexandre Proutiere, Se-Young Yun

To this end, we revisit instance-specific lower bounds on the expected number of misclassified items satisfied by any clustering algorithm.

Clustering Stochastic Block Model

FedSOL: Stabilized Orthogonal Learning in Federated Learning

no code implementations24 Aug 2023 Gihun Lee, Minchan Jeong, Sangmook Kim, Jaehoon Oh, Se-Young Yun

FedSOL is designed to identify gradients of local objectives that are inherently orthogonal to directions affecting the proximal objective.

Federated Learning

Cross-Modal Retrieval Meets Inference:Improving Zero-Shot Classification with Cross-Modal Retrieval

no code implementations29 Aug 2023 Seongha Eom, Namgyu Ho, Jaehoon Oh, Se-Young Yun

Given a query image, we harness the power of CLIP's cross-modal representations to retrieve relevant textual information from an external image-text pair dataset.

Cross-Modal Retrieval Image Classification +3

Non-backtracking Graph Neural Networks

no code implementations11 Oct 2023 Seonghyun Park, Narae Ryu, Gahee Kim, Dongyeop Woo, Se-Young Yun, Sungsoo Ahn

In this work, we propose to resolve such a redundancy via the non-backtracking graph neural network (NBA-GNN) that updates a message without incorporating the message from the previously visited node.

Node Classification Stochastic Block Model

Fine tuning Pre trained Models for Robustness Under Noisy Labels

no code implementations24 Oct 2023 Sumyeong Ahn, Sihyeon Kim, Jongwoo Ko, Se-Young Yun

To tackle this issue, researchers have explored methods for Learning with Noisy Labels to identify clean samples and reduce the influence of noisy labels.

Denoising Learning with noisy labels

Fine-Tuning the Retrieval Mechanism for Tabular Deep Learning

no code implementations13 Nov 2023 Felix den Breejen, Sangmin Bae, Stephen Cha, Tae-Young Kim, Seoung Hyun Koh, Se-Young Yun

While interests in tabular deep learning has significantly grown, conventional tree-based models still outperform deep learning methods.

Retrieval Transfer Learning

Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models

no code implementations14 Nov 2023 Yujin Kim, Jaehong Yoon, Seonghyeon Ye, Sung Ju Hwang, Se-Young Yun

In an ever-evolving world, the dynamic nature of knowledge presents challenges for language models that are trained on static data, leading to outdated encoded information.

Continual Learning Question Answering +1

FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learning

no code implementations22 Nov 2023 Seongyoon Kim, Gihun Lee, Jaehoon Oh, Se-Young Yun

Additionally, we observe that as data heterogeneity increases, the gap between higher feature norms for observed classes, obtained from local models, and feature norms of unobserved classes widens, in contrast to the behavior of classifier weight norms.

Federated Learning

Revisiting Early-Learning Regularization When Federated Learning Meets Noisy Labels

no code implementations8 Feb 2024 Taehyeon Kim, Donggyu Kim, Se-Young Yun

In the evolving landscape of federated learning (FL), addressing label noise presents unique challenges due to the decentralized and diverse nature of data collection across clients.

Federated Learning Memorization

Non-linear Fusion in Federated Learning: A Hypernetwork Approach to Federated Domain Generalization

no code implementations10 Feb 2024 Marc Bartholet, Taehyeon Kim, Ami Beuret, Se-Young Yun, Joachim M. Buhmann

We propose an innovative federated algorithm, termed hFedF for hypernetwork-based Federated Fusion, designed to bridge the performance gap between generalization and personalization, capable of addressing various degrees of domain shift.

Domain Generalization Federated Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.