Zobrazeno 1 - 10
of 821
pro vyhledávání: '"Feng, Shengyu"'
Autor:
Feng, Shengyu, Tong, Hanghang
The advances in deep learning have enabled machine learning methods to outperform human beings in various areas, but it remains a great challenge for a well-trained model to quickly adapt to a new task. One promising solution to realize this goal is
Externí odkaz:
http://arxiv.org/abs/2301.07850
Contrastive learning is an effective unsupervised method in graph representation learning, and the key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the proximity of node
Externí odkaz:
http://arxiv.org/abs/2208.06956
Contrastive learning is an effective unsupervised method in graph representation learning. Recently, the data augmentation based contrastive learning method has been extended from images to graphs. However, most prior works are directly adapted from
Externí odkaz:
http://arxiv.org/abs/2202.06491
Dynamic scene graph generation from a video is challenging due to the temporal dynamics of the scene and the inherent temporal fluctuations of predictions. We hypothesize that capturing long-term temporal dependencies is the key to effective generati
Externí odkaz:
http://arxiv.org/abs/2112.09828
Graphs are powerful representations for relations among objects, which have attracted plenty of attention. A fundamental challenge for graph learning is how to train an effective Graph Neural Network (GNN) encoder without labels, which are expensive
Externí odkaz:
http://arxiv.org/abs/2109.03560
Publikováno v:
In Colloids and Surfaces A: Physicochemical and Engineering Aspects 20 June 2024 691
Publikováno v:
In European Polymer Journal 10 June 2024 213
Publikováno v:
In Polymer 5 January 2024 290
Publikováno v:
In Colloids and Surfaces A: Physicochemical and Engineering Aspects 5 October 2023 674
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.