The paper 'THOR: Self-Supervised Temporal Knowledge Graph Embedding via Three-Tower Graph Convolutional Networks' has been accepted in a top conference, IEEE ICDM 2022

게시자: 안지원, 2022. 9. 2. 오후 6:27   [ 2022. 9. 2. 오후 7:08에 업데이트됨 ]

아래 논문이 top conference 인 IEEE International Conference on Data Mining (IEEE ICDM 2022) 에 accept 되었습니다.
IEEE ICDM은 BK21 최우수국제학술대회목록에서 impact factor (IF) 3점으로 인정 받는 computer science (CS) 분야의 최상위 학술대회입니다.

축하합니다.

Title: THOR: Self-Supervised Temporal Knowledge Graph Embedding via Three-Tower Graph Convolutional Networks
Author: Yeon-Chang Lee*, JaeHyun Lee*, Dongwon Lee, and Sang-Wook Kim
Abstract
The goal of temporal knowledge graph embedding (TKGE) is to represent the entities and relations in a given temporal knowledge graph (TKG) as low-dimensional vectors (i.e., embeddings), which preserve both semantic information and temporal dynamics of the factual information. In this paper, we posit that the intrinsic difficulty of existing TKGE methods lies in the lack of information in KG snapshots with timestamps, each of which contains the facts that co-occur at a specific timestamp. To address this challenge, we propose a novel self-supervised TKGE approach, THOR (Three-tower grapH cOnvolution netwoRks (GCNs)), which extracts latent knowledge from TKGs by jointly leveraging both temporal and atemporal dependencies between entities and the structural dependency between relations. THOR learns the embeddings of entities and relations, obtained from three-tower GCNs, via the following two objectives: (1) to maximize the likelihood of the facts in a TKG; (2) to address the lack of information in a TKG based on auxiliary supervision signals of each entity. Our experiments on three real-world datasets demonstrate that THOR significantly outperforms 13 competitors in terms of TKG completion tasks. THOR yields up to 9.37% higher accuracy, compared to the best competitor.

The paper 'Phishing URL Detection: A Network-based Approach Robust to Evasion' has been accepted in a top conference, ACM CCS 2022

게시자: 안지원, 2022. 8. 29. 오후 5:57   [ 2022. 9. 2. 오후 6:32에 업데이트됨 ]

아래 논문이 top conference 인 ACM Conference on Computer and Communications Security (ACM CCS 2022) 에 accept 되었습니다.
ACM CCS는 BK21 최우수국제학술대회목록에서 impact factor (IF) 4점으로 인정 받는 computer science (CS) 분야의 최상위 학술대회입니다.

축하합니다.

Title: Phishing URL Detection: A Network-based Approach Robust to Evasion
Author: Taeri Kim*, Noseong Park*, Jiwon Hong, and Sang-Wook Kim
Abstract
Many cyberattacks start with disseminating phishing URLs. When clicking these phishing URLs, the victim’s private information is leaked to the attacker. There have been proposed several machine learning methods to detect phishing URLs. However, it still remains under-explored to detect phishing URLs with evasion, i.e., phishing URLs that pretend to be benign by manipulating patterns. In many cases, the attacker i) reuses prepared phishing web pages because making a completely brand-new set costs non-trivial expenses, ii) prefers hosting companies that do not require private information and are cheaper than others, iii) prefers shared hosting for cost efficiency, and iv) sometimes uses benign domains, IP addresses, URL string patterns to evade existing detection methods. Inspired by those behavioral characteristics, we present a network-based inference method to accurately detect phishing URLs camouflaged with legitimate patterns, i.e., robust to evasion. In the network approach, a phishing URL will be still identified as phishy even after evasion unless a majority of its neighbors in the network are evaded at the same time. Our method consistently shows better detection performance throughout various experimental tests than state-of-the-art methods, e.g., F-1 of 0.89 for our method vs. 0.84 for the best feature-based method.

The paper 'MARIO: Modality-Aware Attention and Modality-Preserving Decoders for Multimedia Recommendation' has been accepted in a top conference, ACM CIKM 2022

게시자: 안지원, 2022. 8. 4. 오후 10:45   [ 2022. 8. 21. 오후 7:11에 업데이트됨 ]

아래 논문이 top conference 인 ACM International Conference on Information and Knowledge Management (ACM CIKM 2022) 에 accept 되었습니다.
ACM CIKM는 BK21 최우수국제학술대회목록에서 impact factor (IF) 3점으로 인정 받는 computer science (CS) 분야의 최상위 학술대회입니다.

Title: MARIO: Modality-Aware Attention and Modality-Preserving Decoders for Multimedia Recommendation
Author: Taeri Kim, Yeon-Chang Lee, Kijung Shin and Sang-Wook Kim

축하합니다.

The paper 'RealGraph-GPU: A High-Performance GPU-Based Graph Engine toward Large-Scale Real-World Network Analysis' has been accepted in a top conference, ACM CIKM 2022

게시자: 안지원, 2022. 8. 4. 오후 10:39   [ 2022. 8. 21. 오후 7:12에 업데이트됨 ]

아래 논문이 top conference 인 ACM International Conference on Information and Knowledge Management (ACM CIKM 2022) 에 accept 되었습니다.
ACM CIKM는 BK21 최우수국제학술대회목록에서 impact factor (IF) 3점으로 인정 받는 computer science (CS) 분야의 최상위 학술대회입니다.

Title: RealGraph-GPU: A High-Performance GPU-Based Graph Engine toward Large-Scale Real-World Network Analysis
Author: Myung-Hwan Jang, Yunyong Ko, Dongkyu Jeong, Jeong-Min Park and Sang-Wook Kim

축하합니다.

The paper 'Context-aware Traffic Forecasting of New Roads' has been accepted in a top conference, ACM CIKM 2022

게시자: 안지원, 2022. 8. 4. 오후 10:36   [ 2022. 8. 21. 오후 7:12에 업데이트됨 ]

아래 논문이 top conference 인 ACM International Conference on Information and Knowledge Management (ACM CIKM 2022) 에 accept 되었습니다.
ACM CIKM는 BK21 최우수국제학술대회목록에서 impact factor (IF) 3점으로 인정 받는 computer science (CS) 분야의 최상위 학술대회입니다.

Title: Context-aware Traffic Forecasting of New Roads
Author: Namhyuk Kim, Dong-Kyu Chae, Jung Ah Shin, Sang-Wook Kim, Duen Horng Chau and Sunghwan Park

축하합니다.

The paper 'ST-GAT: Spatio-Temporal Graph Attention Network for Traffic Speed Prediction' has been accepted in a top conference, ACM CIKM 2022

게시자: 안지원, 2022. 8. 4. 오후 10:35   [ 2022. 8. 21. 오후 7:13에 업데이트됨 ]

아래 논문이 top conference 인 ACM International Conference on Information and Knowledge Management (ACM CIKM 2022) 에 accept 되었습니다.
ACM CIKM는 BK21 최우수국제학술대회목록에서 impact factor (IF) 3점으로 인정 받는 computer science (CS) 분야의 최상위 학술대회입니다.

Title: ST-GAT: Spatio-Temporal Graph Attention Network for Traffic Speed Prediction
Author: Junho Song, Dong-hyuk Seo, Jiwon Son, Namhyuk Kim and Sang-Wook Kim

축하합니다.

The paper 'Is It Enough Just Looking at the Title?: Leveraging Body Text To Enrich Title Words Towards Accurate News Recommendation' has been accepted in a top conference, ACM CIKM 2022

게시자: 안지원, 2022. 8. 4. 오후 10:33   [ 2022. 9. 2. 오후 9:03에 업데이트됨 ]

아래 논문이 top conference 인 ACM International Conference on Information and Knowledge Management (ACM CIKM 2022) 에 accept 되었습니다.
ACM CIKM는 BK21 최우수국제학술대회목록에서 impact factor (IF) 3점으로 인정 받는 computer science (CS) 분야의 최상위 학술대회입니다.

Title: Is It Enough Just Looking at the Title?: Leveraging Body Text To Enrich Title Words Towards Accurate News Recommendation
Author: Taeho Kim*, Yungi Kim*, Yeon-Chang Lee, Won-Yong Shin and Sang-Wook Kim

축하합니다.

'복수개의 커뮤니티를 포함하는 네트워크에서 커뮤니티 재구성 방법 및 이를 위한 전자 장치'가 특허 등록되었습니다.

게시자: 안지원, 2022. 7. 21. 오전 2:02

강윤석, 이준석 연구원의 연구 결과인 '복수개의 커뮤니티를 포함하는 네트워크에서 커뮤니티 재구성 방법 및 이를 위한 전자 장치'가 특허 최종 등록되었습니다.

축하합니다.

The paper 'Effective and Efficient Negative Sampling in Metric Learning based Recommendation' has been accepted in Information Sciences

게시자: 안지원, 2022. 5. 12. 오전 5:24

아래 논문이 SCI 저널인 Information Sciences 에 accept 되었습니다. Information Sciences 저널은 SCI 저널들 중에서도 상위 5%에 속하는 최상위 저널입니다.

Title: Effective and Efficient Negative Sampling in Metric Learning based Recommendation
Author: Junha Park*, Yeon-Chang Lee*, and Sang-Wook Kim
 
축하합니다.

'부호 검증을 통한 랜덤 워크 기반 개인화된 노드 랭킹 방법 및 장치'가 국제 특허로 출원되었습니다

게시자: 안지원, 2022. 5. 3. 오전 4:21   [ 2022. 5. 3. 오전 4:22에 업데이트됨 ]

이원창, 이연창 연구원의 연구 결과인 '부호 검증을 통한 랜덤 워크 기반 개인화된 노드 랭킹 방법 및 장치'가 국제 특허로 출원되었습니다.

축하합니다.

1-10 of 182