Taking Human out of Learning Applications: A Survey on Automated Machine Learning

Yao, Quanming; Wang, Mengshuo; Chen, Yuqiang; Dai, Wenyuan; Li, Yu-Feng; Tu, Wei-Wei; Yang, Qiang; Yu, Yang

doi:10.48550/arxiv.1810.13306

Cited by 102 publications

(129 citation statements)

References 107 publications

(241 reference statements)

Supporting

Mentioning

126

Contrasting

Unclassified

Order By: Relevance

“…As for the future works, we plan to search graph structure (Zhao et al, 2021) and utilize automated machine learning (Yao et al, 2018) to improve learning performance.…”

Section: Discussionmentioning

confidence: 99%

Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification

Wang

Wang²,

Yao

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Short text classification is a fundamental task in natural language processing. It is hard due to the lack of context information and labeled data in practice. In this paper, we propose a new method called SHINE, which is based on graph neural network (GNN), for short text classification. First, we model the short text dataset as a hierarchical heterogeneous graph consisting of word-level component graphs which introduce more semantic and syntactic information. Then, we dynamically learn a short document graph that facilitates effective label propagation among similar short texts. Thus, comparing with existing GNN-based methods, SHINE can better exploit interactions between nodes of the same types and capture similarities between short texts. Extensive experiments on various benchmark short text datasets show that SHINE consistently outperforms state-of-the-art methods, especially with fewer labels. 1

show abstract

“…As for the future works, we plan to search graph structure (Zhao et al, 2021) and utilize automated machine learning (Yao et al, 2018) to improve learning performance.…”

Section: Discussionmentioning

confidence: 99%

Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification

Wang

Wang²,

Yao

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The search for the hyperparameters to use is an optimization problem, which is often solved heuristically in a trial-and-error manner. In extreme cases, the trial-and-error process can be automated, and this is known as automated machine learning [60]. In all cases, the higher the complexity of the model and the task, the longer the time per trial would be.…”

Section: A a Study Into Falcon's Configurationmentioning

confidence: 99%

FALCON: Fast and Accurate Multipath Scheduling using Offline and Online Learning

Wu¹,

Alay²,

Brunström³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multipath transport protocols enable the concurrent use of different network paths, benefiting a fast and reliable data transmission. The scheduler of a multipath transport protocol determines how to distribute data packets over different paths. Existing multipath schedulers either conform to predefined policies or to online trained policies. The adoption of millimeter wave (mmWave) paths in 5th Generation (5G) networks and Wireless Local Area Networks (WLANs) introduces timevarying network conditions, under which the existing schedulers struggle to achieve fast and accurate adaptation. In this paper, we propose FALCON, a learning-based multipath scheduler that can adapt fast and accurately to time-varying network conditions. FALCON builds on the idea of meta-learning where offline learning is used to create a set of meta-models that represent coarse-grained network conditions, and online learning is used to bootstrap a specific model for the current fine-grained network conditions towards deriving the scheduling policy to deal with such conditions. Using trace-driven emulation experiments, we demonstrate FALCON outperforms the best state-of-the-art scheduler by up to 19.3% and 23.6% in static and mobile networks, respectively. Furthermore, we show FALCON is quite flexible to work with different types of applications such as bulk transfer and web services. Moreover, we observe FALCON has a much faster adaptation time compared to all the other learningbased schedulers, reaching almost an 8-fold speedup compared to the best of them. Finally, we have validated the emulation results in real-world settings illustrating that FALCON adapts well to the dynamicity of real networks, consistently outperforming all other schedulers.

show abstract

“…Recommendation scenarios are diverse and largely different from each other; thus, there exists no silver bullet GNN model that can generalize across all scenarios. Recently, AutoML (Automated Machine Learning) [187] is proposed, which can automatically design appropriate models for specific tasks. With respect to GNN-based recommendation, the search space is quite large, which includes multiple options for the neighbor sampler, aggregator, interaction function, and so on.…”

Section: Automl-enhanced Gnnmentioning

confidence: 99%

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

Chen¹,

Zheng²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recommender system is one of the most important information services on today's Internet. Recently, graph neural networks have become the new state-of-the-art approach of recommender systems. In this survey, we conduct a comprehensive review of the literature in graph neural network-based recommender systems. We first introduce the background and the history of the development of both recommender systems and graph neural networks. For recommender systems, in general, there are four aspects for categorizing existing works: stage, scenario, objective, and application. For graph neural networks, the existing methods consist of two categories, spectral models and spatial ones. We then discuss the motivation of applying graph neural networks into recommender systems, mainly consisting of the high-order connectivity, the structural property of data, and the enhanced supervision signal. We then systematically analyze the challenges in graph construction, embedding propagation/aggregation, model optimization, and computation efficiency. Afterward and primarily, we provide a comprehensive overview of a multitude of existing works of graph neural network-based recommender systems, following the taxonomy above. Finally, we raise discussions on the open problems and promising future directions of this area. We summarize the representative papers along with their codes repositories in https://github.com/tsinghua-fib-lab/GNN-Recommender-Systems.

show abstract

Taking Human out of Learning Applications: A Survey on Automated Machine Learning

Cited by 102 publications

References 107 publications

Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification

Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification

FALCON: Fast and Accurate Multipath Scheduling using Offline and Online Learning

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

Contact Info

Product

Resources

About