Jae-Gil Lee

Jae-Gil Lee

Auto-generated profile, based on publicly available information

Jae-Gil Lee

Korea Advanced Institute of Science and Technology (KAIST)

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 March 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
HSHwanjun Song
Hwanjun Song
MKMinseok Kim
Minseok Kim
DPDongmin Park
Dongmin Park
YSYooju Shin
Yooju Shin
JLJae-Gil Lee
Jae-Gil Lee
Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy labels severely degrade the generalization performance of deep neural networks, learning from noisy labels (robust training) is becoming an important task in modern deep learning applications. In this survey, we first describe the problem of learning with label noise from a supervised learning perspective. Next, we provide a comprehensive review of 62 state-of-the-art robust training methods, all of which are categorized into five groups according to their methodological difference, followed by a systematic comparison of six properties used to evaluate their superiority. Subsequently, we perform an in-depth analysis of noise rate estimation and summarize the typically used evaluation methodology, including public noisy datasets and evaluation metrics. Finally, we present several promising research directions that can serve as a guideline for future studies.

3 January 2023 in The VLDB Journal
Verified
Journal Article
Closed access
PDF file
SWSteven Euijong Whang
Steven Euijong Whang
YRYuji Roh
Yuji Roh
HSHwanjun Song
Hwanjun Song
JLJae-Gil Lee
Jae-Gil Lee

20 January 2023 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
PTPatara Trirat
Patara Trirat
SYSusik Yoon
Susik Yoon
JLJae-Gil Lee
Jae-Gil Lee
Due to the continuing colossal socio-economic losses caused by traffic accidents, it is of prime importance to precisely forecast the traffic accident risk to reduce future accidents. In this paper, we use dangerous driving statistics from driving log data and multi-graph learning to enhance predictive performance. We first conduct geographical and temporal correlation analyses to quantify the relationship between dangerous driving and actual accidents. Then, to learn various dependencies between districts besides the traditional adjacency matrix, we simultaneously model both static and dynamic graphs representing the spatio-temporal contextual relationships with heterogeneous environmental data, including the dangerous driving behavior A graph is generated for each type of the relationships. Ultimately, we propose an end-to-end framework, called, to effectively learn the association of multiple graphs for accident risk prediction by adopting multi-view graph neural networks with a multi-attention module. Thorough experiments on ten real-world datasets show that, compared with state-of-the-art methods, reduces the error of predicting the accident risk by up to 23% and improves the accuracy of predicting the most dangerous areas by up to 27%.

13 May 2024
Verified
Conference Paper
Open access
YNYoungeun Nam
Youngeun Nam
SYSusik Yoon
Susik Yoon
YSYooju Shin
Yooju Shin
MBMinyoung Bae
Minyoung Bae
HSHwanjun Song
Hwanjun Song
BLByung Suk Lee
Byung Suk Lee
In light of the remarkable advancements made in time-series anomaly detection(TSAD), recent emphasis has been placed on exploiting the frequency domain as well as the time domain to address the difficulties in precisely detecting pattern-wise anomalies. However, in terms of anomaly scores, the window granularity of the frequency domain is inherently distinct from the data-point granularity of the time domain. Owing to this discrepancy, the anomaly information in the frequency domain has not been utilized to its full potential for TSAD. In this paper, we propose a TSAD framework, Dual-TF, that simultaneously uses both the time and frequency domains while breaking the time-frequency granularity discrepancy. To this end, our framework employs nested-sliding windows, with the outer and inner windows responsible for the time and frequency domains, respectively, and aligns the anomaly scores of the two domains. As a result of the high resolution of the aligned scores, the boundaries of pattern-wise anomalies can be identified more precisely. In six benchmark datasets, our framework outperforms state-of-the-art methods by 12.0--147%, as demonstrated by experimental results.

4 September 2020 in Machine Learning
Verified
Journal Article
Closed access
PDF file
HSHwanjun Song
Hwanjun Song
SKSundong Kim
Sundong Kim
MKMinseok Kim
Minseok Kim
JLJae-Gil Lee
Jae-Gil Lee

11 February 2020 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
SHS. K. Hong
S. K. Hong
JLJae-Gil Lee
Jae-Gil Lee
Background: Biomedical named-entity recognition (BioNER) is widely modeled with conditional random fields (CRF) by regarding it as a sequence labeling problem. The CRF-based methods yield structured outputs of labels by imposing connectivity between the labels. Recent studies for BioNER have reported state-of-the-art performance by combining deep learning-based models (e.g., bidirectional Long Short-Term Memory) and CRF. The deep learning-based models in the CRF-based methods are dedicated to estimating individual labels, whereas the relationships between connected labels are described as static numbers; thereby, it is not allowed to timely reflect the context in generating the most plausible label-label transitions for a given input sentence. Regardless, correctly segmenting entity mentions in biomedical texts is challenging because the biomedical terms are often descriptive and long compared with general terms. Therefore, limiting the label-label transitions as static numbers is a bottleneck in the performance improvement of BioNER. Results: We introduce DTranNER, a novel CRF-based framework incorporating a deep learning-based label-label transition model into BioNER. DTranNER uses two separate deep learning-based networks: Unary-Network and Pairwise-Network. The former is to model the input for determining individual labels, and the latter is to explore the context of the input for describing the label-label transitions. We performed experiments on five benchmark BioNER corpora. Compared with current state-of-the-art methods, DTranNER achieves the best F1-score of 84.56% beyond 84.40% on the BioCreative II gene mention (BC2GM) corpus, the best F1-score of 91.99% beyond 91.41% on the BioCreative IV chemical and drug (BC4CHEMD) corpus, the best F1-score of 94.16% beyond 93.44% on the chemical NER, the best F1-score of 87.22% beyond 86.56% on the disease NER of the BioCreative V chemical disease relation (BC5CDR) corpus, and a near-best F1-score of 88.62% on the NCBI-Disease corpus. Conclusions: Our results indicate that the incorporation of the deep learning-based label-label transition model provides distinctive contextual clues to enhance BioNER over the static transition model. We demonstrate that the proposed framework enables the dynamic transition model to adaptively explore the contextual relations between adjacent labels in a fine-grained way. We expect that our study can be a stepping stone for further prosperity of biomedical literature mining.