Author name cluster

Yejin Kim

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

ICML Conference 2025 Conference Paper

Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective

Joonkyu Kim
Yejin Kim
Jy-yong Sohn

In continual learning scenarios, catastrophic forgetting of previously learned tasks is a critical issue, making it essential to effectively measure such forgetting. Recently, there has been growing interest in focusing on representation forgetting, the forgetting measured at the hidden layer. In this paper, we provide the first theoretical analysis of representation forgetting and use this analysis to better understand the behavior of continual learning. First, we introduce a new metric called representation discrepancy, which measures the difference between representation spaces constructed by two snapshots of a model trained through continual learning. We demonstrate that our proposed metric serves as an effective surrogate for the representation forgetting while remaining analytically tractable. Second, through mathematical analysis of our metric, we derive several key findings about the dynamics of representation forgetting: the forgetting occurs more rapidly to a higher degree as the layer index increases, while increasing the width of the network slows down the forgetting process. Third, we support our theoretical findings through experiments on real image datasets, including Split-CIFAR100 and ImageNet1K.

Details

NeurIPS Conference 2025 Conference Paper

OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation

Dongjun Hwang
Yejin Kim
Minyoung Lee
Seong Joon Oh
Junsuk Choe

Open-Vocabulary Segmentation (OVS) aims to segment classes that are not present in the training dataset. However, most existing studies assume that the training data is fixed in advance, overlooking more practical scenarios where new datasets are continuously collected over time. To address this, we first analyze how existing OVS models perform under such conditions. In this context, we explore several approaches such as retraining, fine-tuning, and continual learning but find that each of them has clear limitations. To address these issues, we propose ConOVS, a novel continual learning method based on a Mixture-of-Experts framework. ConOVS dynamically combines expert decoders based on the probability that an input sample belongs to the distribution of each incremental dataset. Through extensive experiments, we show that ConOVS consistently outperforms existing methods across pre-training, incremental, and zero-shot test datasets, effectively expanding the recognition capabilities of OVS models when data is collected sequentially.

PDF Details

EAAI Journal 2024 Journal Article

Multi-attention recommender system for non-fungible tokens

Yejin Kim
Seonmi Kim
Youngbin Lee
Joohwan Hong
Yongjae Lee

Recommender systems have become essential tools for enhancing user experiences across various domains. While extensive research has been conducted on recommender systems for movies, music, and e-commerce, the rapidly growing and economically significant Non-Fungible Token (NFT) market remains underexplored. Recommender systems have the potential to significantly enhance user engagement, increase the time users spend on platforms, and deepen user involvement. Consequently, effective implementation of such systems could serve as a catalyst for invigorating the NFT market. However, the unique characteristics of the NFT market, such as the high sparsity of user–item interactions, anonymity of blockchain, and dual nature, present challenges not encountered in traditional recommender systems, highlighting the importance of developing tailored solutions to cater to its specific needs and unlock its full potential. In this paper, we examine the distinctive characteristics of NFTs and propose the first recommender system specifically designed to address NFT market challenges. In specific, we develop a Multi-Attention Recommender System for NFTs (NFT-MARS) with three key characteristics: (1) graph attention to handle sparse user–item interactions, (2) multi-modal attention to incorporate feature preference of users, and (3) multi-task learning to consider the dual nature of NFTs as both artwork and financial assets. We demonstrate the effectiveness of NFT-MARS compared to various baseline models using the actual transaction data of NFTs collected directly from the blockchain for four of the most popular NFT collections.

Details DOI

IJCAI Conference 2019 Conference Paper

Sequential and Diverse Recommendation with Long Tail

Yejin Kim
Kwangseob Kim
Chanyoung Park
Hwanjo Yu

Sequential recommendation is a task that learns a temporal dynamic of a user behavior in sequential data and predicts items that a user would like afterward. However, diversity has been rarely emphasized in the context of sequential recommendation. Sequential and diverse recommendation must learn temporal preference on diverse items as well as on general items. Thus, we propose a sequential and diverse recommendation model that predicts a ranked list containing general items and also diverse items without compromising significant accuracy. To learn temporal preference on diverse items as well as on general items, we cluster and relocate consumed long tail items to make a pseudo ground truth for diverse items and learn the preference on long tail using recurrent neural network, which enables us to directly learn a ranking function. Extensive online and offline experiments deployed on a commercial platform demonstrate that our models significantly increase diversity while preserving accuracy compared to the state-of-the-art sequential recommendation model, and consequently our models improve user satisfaction.

PDF Details