Hierarchical multi-label classification with chained neural networks

Wehrmann, Jônatas; Barros, Rodrigo C.; Dôres, Silvia N. das; Cerri, Ricardo

doi:10.1145/3019612.3019664

Cited by 126 publications

(207 citation statements)

References 16 publications

Supporting

Mentioning

207

Contrasting

Order By: Relevance

“…Secondly, we found that the original performance of HMCN (Wehrmann et al, 2018) is sometimes much lower than expected. After tuning their model, we observed that if we first conduct a weighted sum of the local and global outputs and then apply the sigmoid function, the performance of HMCN becomes much better (see Table 7) than doing them in the opposite order as in Wehrmann et al (2018). In addition, we found that HMCN + HAN (Yang et al, 2016) would result in extremely low performance.…”

Section: B Performance Analysis Of Baselinesmentioning

confidence: 69%

“…There are not many neural methods that specifically target HTC. We mainly compare with two latest neural models: HR-DGCNN (Peng et al, 2018), which extends hierarchical regularization (Gopal and Yang, 2013) to Graph-CNN and compares favorably to flat models like RCNN (Lai et al, 2015) and XML-CNN (Liu et al, 2017), and HMCN (Wehrmann et al, 2018), which outperforms state-of-the-art HTC methods such as HMC-LMLP (Cerri et al, 2016). We also compare with the base models that we use for feature encoding.…”

Section: Compared Methodsmentioning

confidence: 99%

“…We use the same raw features as the input of all the methods for apples-to-apples comparison and list the results in Table 4. Note that the metric area under the average precision-recall curve (AUPRC) (Wehrmann et al, 2018) is not applicable because HiLAP does not use a flat probability distribution of all the labels. As one can see, HiLAP outperforms all the baselines on both datasets by a large margin.…”

Section: Methodsmentioning

confidence: 99%

“…To summarize, HiLAP achieves better effectiveness compared to flat and local approaches as it examines the label hierarchy during both training and inference. HiLAP has more flexibility and generalization capacity than previous global approaches in that it has no constraints on the structure of the hierarchy or the labels of the objects (Cai and Hofmann, 2004), generalizes to neural representation learning models (Gopal and Yang, 2013), and makes inter-dependent predictions while ensuring label consistency (Wehrmann et al, 2018;Peng et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Hierarchical Text Classification with Reinforced Label Assignment

Mao

Tian²,

Han³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

While existing hierarchical text classification (HTC) methods attempt to capture label hierarchies for model training, they either make local decisions regarding each label or completely ignore the hierarchy information during inference. To solve the mismatch between training and inference as well as modeling label dependencies in a more principled way, we formulate HTC as a Markov decision process and propose to learn a Label Assignment Policy via deep reinforcement learning to determine where to place an object and when to stop the assignment process. The proposed method, HiLAP, explores the hierarchy during both training and inference time in a consistent manner and makes inter-dependent decisions. As a general framework, HiLAP can incorporate different neural encoders as base models for end-to-end training. Experiments on five public datasets and four base models show that HiLAP yields an average improvement of 33.4% in Macro-F1 over flat classifiers and outperforms state-of-the-art HTC methods by a large margin. 1 1 Data and code can be found at https://github.com/ morningmoni/HiLAP. STOP is taken t = 0 t = 1 t = 2 t = 6 0 ROOT

show abstract

Section: B Performance Analysis Of Baselinesmentioning

confidence: 69%

Section: Compared Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hierarchical Text Classification with Reinforced Label Assignment

Mao

Tian²,

Han³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

show abstract

“…Concretely, we select a best model through coarse-grained experiments on each of the two benchmarks and fix it, and then fine-tune the features and hyperparameters, such as model structures, input representations, activation functions, optimizers, learning rate, etc. The best performance models 6 are as Models RCV1 Yelp Micro-F1 Micro-F1 HR-DGCNN (Peng et al, 2018) 0.7610 -HMCN (Wehrmann et al, 2018) 0.8080 0.6640 Our best models 0.8099 0.6704 follows: (1) RCNN with two-layers Bi-GRU and one-layer CNN for RCV1 dataset (input = word, optimizer = Adam, learning rate = 0.008);…”

Section: Results Of Using Rich Models and Featuresmentioning

confidence: 99%

NeuralClassifier: An Open-source Neural Hierarchical Multi-label Text Classification Toolkit

Liu¹,

Mu²,

Li³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

View full text Add to dashboard Cite

In this paper, we introduce NeuralClassifier, a toolkit for neural hierarchical multi-label text classification. NeuralClassifier is designed for quick implementation of neural models for hierarchical multi-label classification task, which is more challenging and common in real-world scenarios. A salient feature is that NeuralClassifier currently provides a variety of text encoders, such as FastText, TextCNN, TextRNN, RCNN, VDCNN, DPCNN, DRNN, AttentiveConvNet and Transformer encoder, etc. It also supports other text classification scenarios, including binary-class and multiclass classification. Built on PyTorch 1 , the core operations are calculated in batch, making the toolkit efficient with the acceleration of GPU. Experiments show that models built in our toolkit achieve comparable performance with reported results in the literature.

show abstract

Hierarchical multilabel classifier for gene ontology annotation using multihead and multiend deep CNN model

Yuan

Pang

Lin

et al. 2020

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Gene ontology annotation is known to be a very complicated multilabel classification task, and the hierarchical multilabel classification (HMC) approaches with local classifiers have been shown to be effective for the task. In a traditional HMC method, a set of hierarchically organized simple local classifiers are usually used, each of which for one hierarchical level separately. In this paper, we propose a novel hierarchical multilabel classifier implementing the whole set of hierarchically organized local classifiers in one deep convolution neural network (CNN) model with multiple heads and multiple ends (MHME). The proposed MHME CNN model consists of three parts: the body part of a deep CNN model shared by different local classifiers for feature extraction and feature mapping; the multiend part of a set of autoencoders performing feature fusion transforming the input vectors of different local classifiers to feature vectors with the same length so as to share the feature mapping part; and the multihead part of a set of linear multilabel classifiers. Furthermore, a sophisticated recursive algorithm is designed to train the MHME CNN model to realize the functions of a set of hierarchically organized local classifiers. In this way, by sharing a deep CNN with multiple local classifiers, we are able to construct more powerful local classifiers for each level with limited training samples, and to achieve better classification performance. Experiment results on various benchmark datasets show that the proposed deep CNN‐based model has better performance than the state‐of‐the‐art traditional models. Moreover, it gives rather good performance even under a transfer learning. © 2020 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract

Hierarchical multi-label classification with chained neural networks

Cited by 126 publications

References 16 publications

Hierarchical Text Classification with Reinforced Label Assignment

Hierarchical Text Classification with Reinforced Label Assignment

NeuralClassifier: An Open-source Neural Hierarchical Multi-label Text Classification Toolkit

Hierarchical multilabel classifier for gene ontology annotation using multihead and multiend deep CNN model

Contact Info

Product

Resources

About