Neural Structured Learning: Training Neural Networks with Structured Signals

被引：8

作者：

Gopalan, Arjun ^{[1
]}

Juan, Da-Cheng ^{[1
]}

Magalhaes, Cesar Ilharco ^{[2
]}

Ferng, Chun-Sung ^{[1
]}

Heydon, Allan ^{[1
]}

Lu, Chun-Ta ^{[1
]}

Pham, Philip ^{[1
]}

Yu, George ^{[1
]}

Fan, Yicheng ^{[1
]}

Wang, Yueqi ^{[1
]}

机构：

[1] Google Res, Mountain View, CA 94043 USA

[2] Google Res, Zurich, Switzerland

来源：

WSDM '21: PROCEEDINGS OF THE 14TH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING | 2021年

关键词：

Neural networks; Structured signals; Graph learning; Adversarial learning; Regularization; TensorFlow;

D O I：

10.1145/3437963.3441666

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present Neural Structured Learning (NSL) in TensorFlow [1], a new learning paradigm to train neural networks by leveraging structured signals in addition to feature inputs. Structure can be explicit as represented by a graph, or implicit, either induced by adversarial perturbation or inferred using techniques like embedding learning. NSL is open-sourced as part of the TensorFlow [2] ecosystem and is widely used in Google across many products and services. In this tutorial, we provide an overview of the NSL framework including various libraries, tools, and APIs as well as demonstrate the practical use of NSL in different applications. The NSL website is hosted at www.tensorflow.org/neural_structured_learning, which includes details about the theoretical foundations of the technology, extensive API documentation, and hands-on tutorials.

引用

页码：1150 / 1153

页数：4

共 50 条

[21] STRUCTURED NEURAL NETWORKS FOR MARKOVIAN PROCESSES
DODD, N
MCCULLOCH, N
FIRST IEE INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS, 1989, : 319 - 323
[22] Learning Spatiotemporally Encoded Pattern Transformations in Structured Spiking Neural Networks
Gardner, Brian
Sporea, Ioana
Gruening, Andre
NEURAL COMPUTATION, 2015, 27 (12) : 2548 - 2586
[23] Structured Learning in Fuzzy Spiking Neural Networks for Human State Estimation
Obo, Takenori
Kubota, Naoyuki
2014 WORLD AUTOMATION CONGRESS (WAC): EMERGING TECHNOLOGIES FOR A NEW PARADIGM IN SYSTEM OF SYSTEMS ENGINEERING, 2014,
[24] Asynchronous parallel learning for neural networks and structured models with dense features
Sun, Xu (xusun@pku.edu.cn), 1600, Association for Computational Linguistics, ACL Anthology
[25] Neural-Fitted TD-Leaf Learning for Playing Othello With Structured Neural Networks
van den Dries, Sjoerd
Wiering, Marco A.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2012, 23 (11) : 1701 - 1713
[26] Learning structured and non-redundant representations with deep neural networks
Yang, Jihai
Xiong, Wei
Li, Shijun
Xu, Chang
PATTERN RECOGNITION, 2019, 86 : 224 - 235
[27] Learning Low-Rank Structured Sparsity in Recurrent Neural Networks
Wen, Weijing
Yang, Fan
Su, Yangfeng
Zhou, Dian
Zeng, Xuan
2020 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2020,
[28] Self-learning Recursive Neural Networks for Structured Data Classification
Bouchachia, Abdelhamid
Ortner, Alexander
PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2014, : 808 - 815
[29] GigaDepth: Learning Depth from Structured Light with Branching Neural Networks
Schreiberhuber, Simon
Weibel, Jean-Baptiste
Patten, Timothy
Vincze, Markus
COMPUTER VISION - ECCV 2022, PT XXXIII, 2022, 13693 : 214 - 229
[30] Design of MRI structured spiking neural networks and learning algorithms for personalized modelling, analysis, and prediction of EEG signals
Saeedinia, Samaneh Alsadat
Jahed-Motlagh, Mohammad Reza
Tafakhori, Abbas
Kasabov, Nikola
SCIENTIFIC REPORTS, 2021, 11 (01)

← 1 2 3 4 5 →