Zobrazeno 1 - 10
of 154
pro vyhledávání: '"Gao, Jianfei"'
Over the past few years, as large language models have ushered in an era of intelligence emergence, there has been an intensified focus on scaling networks. Currently, many network architectures are designed manually, often resulting in sub-optimal c
Externí odkaz:
http://arxiv.org/abs/2405.07194
The task of inductive link prediction in knowledge graphs (KGs) generally focuses on test predictions with solely new nodes but not both new nodes and new relation types. In this work, we formally define the concept of double permutation-equivariant
Externí odkaz:
http://arxiv.org/abs/2302.01313
In this paper, we seek to answer what-if questions - i.e., given recorded data of an existing deployed networked system, what would be the performance impact if we changed the design of the system (a task also known as causal inference). We make thre
Externí odkaz:
http://arxiv.org/abs/2208.12596
Knowledge distillation(KD) is a widely-used technique to train compact models in object detection. However, there is still a lack of study on how to distill between heterogeneous detectors. In this paper, we empirically find that better FPN features
Externí odkaz:
http://arxiv.org/abs/2207.02039
Autor:
Gao, Jianfei, Ribeiro, Bruno
This work formalizes the associational task of predicting node attribute evolution in temporal graphs from the perspective of learning equivariant representations. We show that node representations in temporal graphs can be cast into two distinct fra
Externí odkaz:
http://arxiv.org/abs/2103.07016
Publikováno v:
In Ceramics International November 2024
Knowledge distillation (KD) has been proven to be a simple and effective tool for training compact models. Almost all KD variants for dense prediction tasks align the student and teacher networks' feature maps in the spatial domain, typically by mini
Externí odkaz:
http://arxiv.org/abs/2011.13256
Publikováno v:
Published as a conference paper at the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020)
We consider the task of learning a parametric Continuous Time Markov Chain (CTMC) sequence model without examples of sequences, where the training data consists entirely of aggregate steady-state statistics. Making the problem harder, we assume that
Externí odkaz:
http://arxiv.org/abs/2002.04186
Autor:
Zhong Zeyu, Haiying Guo, Chunfeng Huang, Xiaoheng Geng, Xinlei Jia, Hongjun Huo, Fanru Li, Gao Jianfei
Publikováno v:
Water Science and Technology, Vol 87, Iss 4, Pp 987-997 (2023)
The single-chamber bio-electrical systems can degrade oily sludge in sediments while generating electricity from the microbial fuel cells (MFCs) and their characteristics in energy and environmental effects have attracted wide international attention
Externí odkaz:
https://doaj.org/article/f60795adf0cb4ff9869b9328eeceb9c4
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.