Search Results for author: Dongjin Lee

Found 10 papers, 6 papers with code

I'm Me, We're Us, and I'm Us: Tri-directional Contrastive Learning on Hypergraphs

1 code implementation9 Jun 2022 Dongjin Lee, Kijung Shin

Although machine learning on hypergraphs has attracted considerable attention, most of the works have focused on (semi-)supervised learning, which may cause heavy labeling costs and poor generalization.

Contrastive Learning Data Augmentation +2

AutoSNN: Towards Energy-Efficient Spiking Neural Networks

1 code implementation30 Jan 2022 Byunggook Na, Jisoo Mok, Seongsik Park, Dongjin Lee, Hyeokjun Choe, Sungroh Yoon

We investigate the design choices used in the previous studies in terms of the accuracy and number of spikes and figure out that they are not best-suited for SNNs.

Neural Architecture Search

New Insights for the Stability-Plasticity Dilemma in Online Continual Learning

1 code implementation17 Feb 2023 Dahuin Jung, Dongjin Lee, Sunwon Hong, Hyemi Jang, Ho Bae, Sungroh Yoon

The aim of continual learning is to learn new tasks continuously (i. e., plasticity) without forgetting previously learned knowledge from old tasks (i. e., stability).

Continual Learning

SliceNStitch: Continuous CP Decomposition of Sparse Tensor Streams

1 code implementation23 Feb 2021 Taehyung Kwon, Inkyu Park, Dongjin Lee, Kijung Shin

SLICENSTITCH changes the starting point of each period adaptively, based on the current time, and updates factor matrices (i. e., outputs of CP decomposition) instantly as new data arrives.

Anomaly Detection Recommendation Systems +1

Robust Factorization of Real-world Tensor Streams with Patterns, Missing Values, and Outliers

1 code implementation16 Feb 2021 Dongjin Lee, Kijung Shin

Consider multiple seasonal time series being collected in real-time, in the form of a tensor stream.

Imputation Time Series +1

Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs

1 code implementation21 Aug 2023 Dongjin Lee, Juho Lee, Kijung Shin

Specifically, before the training procedure of a victim model, which is a TGNN for link prediction, we inject edge perturbations to the data that are unnoticeable in terms of the four constraints we propose, and yet effective enough to cause malfunction of the victim model.

Adversarial Attack Link Prediction

Noise-Robust Deep Spiking Neural Networks with Temporal Information

no code implementations22 Apr 2021 Seongsik Park, Dongjin Lee, Sungroh Yoon

Spiking neural networks (SNNs) have emerged as energy-efficient neural networks with temporal information.

Energy-efficient Knowledge Distillation for Spiking Neural Networks

no code implementations14 Jun 2021 Dongjin Lee, Seongsik Park, Jongwan Kim, Wuhyeong Doh, Sungroh Yoon

On MNIST dataset, our proposed student SNN achieves up to 0. 09% higher accuracy and produces 65% less spikes compared to the student SNN trained with conventional knowledge distillation method.

Knowledge Distillation Model Compression +1

Machine Composition of Korean Music via Topological Data Analysis and Artificial Neural Network

no code implementations29 Mar 2022 Mai Lan Tran, Dongjin Lee, Jae-Hun Jung

In \cite{TPJ}, the new concept of the {\it {\color{black}{Overlap}} matrix} has been proposed, which visualizes how those cycles are interconnected over the music flow, in a matrix form.

Topological Data Analysis

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