Transfer Learning for Boosted Relational Dependency Networks Through Genetic Algorithm

Figueiredo, Leticia Freire de; Paes, Aline; Zaverucha, Gerson

doi:10.1007/978-3-030-97454-1_9

Cited by 5 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To date, dependency networks have been used to solve various tasks such as collective classification [Neville and Jensen, 2003], binary classification [Gámez et al, 2006[Gámez et al, , 2008, multi-label classification [Guo and Gu, 2011], part-of-speech tagging [Tarantola and Blanc, 2002], relation prediction [Figueiredo et al, 2021] and collaborative filtering [Heckerman et al, 2000]. Ours is the first work that combines DNs with sophisticated feature representations and performs joint training over these representations.…”

Section: Related Workmentioning

confidence: 99%

Deep Dependency Networks for Multi-Label Classification

Arya¹,

Gogate²

2023

Preprint

View full text Add to dashboard Cite

We propose a simple approach which combines the strengths of probabilistic graphical models and deep learning architectures for solving the multi-label classification task, focusing specifically on image and video data. First, we show that the performance of previous approaches that combine Markov Random Fields with neural networks can be modestly improved by leveraging more powerful methods such as iterative join graph propagation, integer linear programming, and 1 regularizationbased structure learning. Then we propose a new modeling framework called deep dependency networks, which augments a dependency network, a model that is easy to train and learns more accurate dependencies but is limited to Gibbs sampling for inference, to the output layer of a neural network. We show that despite its simplicity, jointly learning this new architecture yields significant improvements in performance over the baseline neural network. In particular, our experimental evaluation on three video activity classification datasets: Charades, Textually Annotated Cooking Scenes (TACoS), and Wetlab, and three multi-label image classification datasets: MS-COCO, PASCAL VOC, and NUS-WIDE show that deep dependency networks are almost always superior to pure neural architectures that do not use dependency networks.

show abstract

Section: Related Workmentioning

confidence: 99%