Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Hwanjun Song"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:11971-11981
Assessing the impact of the COVID-19 crisis on economies is fundamental to tailor the responses of the governments to recover from the crisis. In this paper, we present a novel approach to assessing the economic impact with a large-scale credit card
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::09e12923e6fd1fdc3e4262855bdd83df
https://doi.org/10.1609/aaai.v36i11.21455
https://doi.org/10.1609/aaai.v36i11.21455
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. :1-19
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 seve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8a5c5ec528ee3415f03a0804db631199
https://doi.org/10.1109/tnnls.2022.3152527
https://doi.org/10.1109/tnnls.2022.3152527
Publikováno v:
2022 IEEE International Conference on Data Mining (ICDM).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5dcefa088b1fabb3e4d5a031397fc0d2
https://doi.org/10.1109/icdm54844.2022.00144
https://doi.org/10.1109/icdm54844.2022.00144
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:4164-4171
Point-of-interest (POI) recommendation has become an important research topic in these days. The user check-in history used as the input to POI recommendation is very imbalanced and noisy because of sparse and missing check-ins. Although sample rewei
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d236a8983bb2682336d408c1bb0440d8
https://doi.org/10.1609/aaai.v35i5.16539
https://doi.org/10.1609/aaai.v35i5.16539
Publikováno v:
Machine Learning. 109:1837-1853
Neural networks converge faster with help from a smart batch selection strategy. In this regard, we propose Ada-Boundary, a novel and simple adaptive batch selection algorithm that constructs an effective mini-batch according to the learning progress
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5b8d45941b63bdb111b2580d69ea1558
https://doi.org/10.1007/s10994-020-05903-6
https://doi.org/10.1007/s10994-020-05903-6
Learning under a continuously changing data distribution with incorrect labels is a desirable real-world problem yet challenging. A large body of continual learning (CL) methods, however, assumes data streams with clean labels, and online learning sc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33f4e4ee284877522016bf066693cc1f
http://arxiv.org/abs/2203.15355
http://arxiv.org/abs/2203.15355
Online recommender systems should be always aligned with users' current interest to accurately suggest items that each user would like. Since user interest usually evolves over time, the update strategy should be flexible to quickly catch users' curr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::551a3128bf72ef3865cfe0f5c56fa74e
http://arxiv.org/abs/2203.10354
http://arxiv.org/abs/2203.10354
Publikováno v:
Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.
Real-world data inevitably contains noisy labels, which induce the poor generalization of deep neural networks. It is known that the network typically begins to rapidly memorize false-labeled samples after a certain point of training. Thus, to counte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::703a9dcd5da432a0b98e6f0065c7db0c
https://doi.org/10.1145/3447548.3467222
https://doi.org/10.1145/3447548.3467222
Publikováno v:
KDD
Responsible AI becomes critical where robustness and fairness must be satisfied together. Traditionally, the two topics have been studied by different communities for different applications. Robust training is designed for noisy or poisoned data wher
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::23d20defc0385415f232cd2e90c7d522
https://doi.org/10.1145/3447548.3470799
https://doi.org/10.1145/3447548.3470799
Data-centric AI is at the center of a fundamental shift in software engineering where machine learning becomes the new software, powered by big data and computing infrastructure. Here software engineering needs to be re-thought where data becomes a f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f195fd10341eece0c29d60ff38a6daa9