Výsledky vyhledávání - "Charu C. Aggarwal"

Self-supervised Short-text Modeling through Auxiliary Context Generation

Autor: Nurendra Choudhary, Charu C. Aggarwal, Karthik Subbian, Chandan K. Reddy

Publikováno v: ACM Transactions on Intelligent Systems and Technology. 13:1-21

Short text is ambiguous and often relies predominantly on the domain and context at hand in order to attain semantic relevance. Existing classification models perform poorly on short text due to data sparsity and inadequate context. Auxiliary context

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::17220aa69775b396eee834c83ff2dec0
https://doi.org/10.1145/3511712

Zobrazit plný text záznamu

DAGAD: Data Augmentation for Graph Anomaly Detection

Autor: Fanzhen Liu, Xiaoxiao Ma, Jia Wu, Jian Yang, Shan Xue, Amin Beheshti, Chuan Zhou, Hao Peng, Quan Z. Sheng, Charu C. Aggarwal

Publikováno v: 2022 IEEE International Conference on Data Mining (ICDM).

Graph anomaly detection in this paper aims to distinguish abnormal nodes that behave differently from the benign ones accounting for the majority of graph-structured instances. Receiving increasing attention from both academia and industry, yet exist

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::907c8a83dcd723157070a474d0e6beb1
https://doi.org/10.1109/icdm54844.2022.00036

Zobrazit plný text záznamu

Adversarial Attacks and Defenses on Graphs

Autor: Han Xu, Charu C. Aggarwal, Jiliang Tang, Wei Jin, Yaxing Li, Yiqi Wang, Shuiwang Ji

Publikováno v: ACM SIGKDD Explorations Newsletter. 22:19-34

Deep neural networks (DNNs) have achieved significant performance in various tasks. However, recent studies have shown that DNNs can be easily fooled by small perturbation on the input, called adversarial attacks.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9f231092499fde14a7cfc2505e469a02
https://doi.org/10.1145/3447556.3447566

Zobrazit plný text záznamu

Improving spectral clustering with deep embedding, cluster estimation and metric learning

Autor: Liang Duan, Charu C. Aggarwal, Saket Sathe, Shuai Ma

Publikováno v: Knowledge and Information Systems. 63:675-694

Spectral clustering is one of the most popular modern clustering algorithms. It is easy to implement, can be solved efficiently, and very often outperforms other traditional clustering algorithms such as k-means. However, spectral clustering could be

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d5b354df08f48458c02c4489ea6856ce
https://doi.org/10.1007/s10115-020-01530-8

Zobrazit plný text záznamu

Information Extraction and Knowledge Graphs

Autor: Charu C. Aggarwal

Publikováno v: Machine Learning for Text ISBN: 9783030966225

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::7da25bdf91fc0bb49d09e5a8da621d57
https://doi.org/10.1007/978-3-030-96623-2_13

Zobrazit plný text záznamu

Classifier Performance and Evaluation

Autor: Charu C. Aggarwal

Publikováno v: Machine Learning for Text ISBN: 9783030966225
Machine Learning for Text ISBN: 9783319735306

Among all machine learning problems, classification is the most well studied, and has the most number of solution methodologies. This embarrassment of riches also leads to the natural problems of model selection and evaluation.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8123f91d860b00f91b6565ce7dbc2fa9
https://doi.org/10.1007/978-3-030-96623-2_7

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání