Extreme multi-label classification refers to supervised multi-label learning involving hundreds of thousands or even millions of labels. Datasets in extreme classification exhibit fit to power-law distribution, i.e. a large fraction of labels have very few positive instances in the data distribution. Most state-of-the-art approaches for extreme multi-label classification attempt to capture correlation among labels by embedding the label matrix to a low-dimensional linear sub-space. However, in the presence of power-law distributed extremely large and diverse label spaces, structural assumptions such as low rank can be easily violated. In this work, we present DiSMEC, which is a large-scale distributed framework for learning one-versus-rest linear classifiers coupled with explicit capacity control to control model size. Unlike most state-of-the-art methods, DiSMEC does not make any low rank assumptions on the label matrix. Using double layer of parallelization, DiSMEC can learn classifiers for datasets consisting hundreds of thousands labels within few hours. The explicit capacity control mechanism filters out spurious parameters which keep the model compact in size, without losing prediction accuracy. We conduct extensive empirical evaluation on publicly available real-world datasets consisting upto 670,000 labels. We compare DiSMEC with recent state-of-the-art approaches, including - SLEEC which is a leading approach for learning sparse local embeddings, and FastXML which is a tree-based approach optimizing ranking based loss function. On some of the datasets, DiSMEC can significantly boost prediction accuracies - 10% better compared to SLECC and 15% better compared to FastXML, in absolute terms.
In this paper, a progressive learning algorithm for multi-label classification to learn new labels while retaining the knowledge of previous labels is designed. New output neurons corresponding to new labels are added and the neural network connections and parameters are automatically restructured as if the label has been introduced from the beginning. This work is the first of the kind in multi-label classifier for class-incremental learning. It is useful for real-world applications such as robotics where streaming data are available and the number of labels is often unknown. Based on the Extreme Learning Machine framework, a novel universal classifier with plug and play capabilities for progressive multi-label classification is developed. Experimental results on various benchmark synthetic and real datasets validate the efficiency and effectiveness of our proposed algorithm.
This paper describes our deep learning-based approach to multilingual aspect-based sentiment analysis as part of SemEval 2016 Task 5. We use a convolutional neural network (CNN) for both aspect extraction and aspect-based sentiment analysis. We cast aspect extraction as a multi-label classification problem, outputting probabilities over aspects parameterized by a threshold. To determine the sentiment towards an aspect, we concatenate an aspect vector with every word embedding and apply a convolution over it. Our constrained system (unconstrained for English) achieves competitive results across all languages and domains, placing first or second in 5 and 7 out of 11 language-domain pairs for aspect category detection (slot 1) and sentiment polarity (slot 3) respectively, thereby demonstrating the viability of a deep learning-based approach for multilingual aspect-based sentiment analysis.
In this paper, we propose a supervised dictionary learning algorithm that aims to preserve the local geometry in both dimensions of the data. A graph-based regularization explicitly takes into account the local manifold structure of the data points. A second graph regularization gives similar treatment to the feature domain and helps in learning a more robust dictionary. Both graphs can be constructed from the training data or learned and adapted along the dictionary learning process. The combination of these two terms promotes the discriminative power of the learned sparse representations and leads to improved classification accuracy. The proposed method was evaluated on several different datasets, representing both single-label and multi-label classification problems, and demonstrated better performance compared with other dictionary based approaches.
The "CNN-RNN" design pattern is increasingly widely applied in a variety of image annotation tasks including multi-label classification and captioning. Existing models use the weakly semantic CNN hidden layer or its transform as the image embedding that provides the interface between the CNN and RNN. This leaves the RNN overstretched with two jobs: predicting the visual concepts and modelling their correlations for generating structured annotation output. Importantly this makes the end-to-end training of the CNN and RNN slow and ineffective due to the difficulty of back propagating gradients through the RNN to train the CNN. We propose a simple modification to the design pattern that makes learning more effective and efficient. Specifically, we propose to use a semantically regularised embedding layer as the interface between the CNN and RNN. Regularising the interface can partially or completely decouple the learning problems, allowing each to be more effectively trained and jointly training much more efficient. Extensive experiments show that state-of-the art performance is achieved on multi-label classification as well as image captioning.
Environmental audio tagging aims to predict only the presence or absence of certain acoustic events in the interested acoustic scene. In this paper we make contributions to audio tagging in two parts, respectively, acoustic modeling and feature learning. We propose to use a shrinking deep neural network (DNN) framework incorporating unsupervised feature learning to handle the multi-label classification task. For the acoustic modeling, a large set of contextual frames of the chunk are fed into the DNN to perform a multi-label classification for the expected tags, considering that only chunk (or utterance) level rather than frame-level labels are available. Dropout and background noise aware training are also adopted to improve the generalization capability of the DNNs. For the unsupervised feature learning, we propose to use a symmetric or asymmetric deep de-noising auto-encoder (sDAE or aDAE) to generate new data-driven features from the Mel-Filter Banks (MFBs) features. The new features, which are smoothed against background noise and more compact with contextual information, can further improve the performance of the DNN baseline. Compared with the standard Gaussian Mixture Model (GMM) baseline of the DCASE 2016 audio tagging challenge, our proposed method obtains a significant equal error rate (EER) reduction from 0.21 to 0.13 on the development set. The proposed aDAE system can get a relative 6.7% EER reduction compared with the strong DNN baseline on the development set. Finally, the results also show that our approach obtains the state-of-the-art performance with 0.15 EER on the evaluation set of the DCASE 2016 audio tagging task while EER of the first prize of this challenge is 0.17.
Hierarchy Of Multi-label classifiers (HOMER) is a multi-label learning algorithm that breaks the initial learning task to several, easier sub-tasks by first constructing a hierarchy of labels from a given label set and secondly employing a given base multi-label classifier (MLC) to the resulting sub-problems. The primary goal is to effectively address class imbalance and scalability issues that often arise in real-world multi-label classification problems. In this work, we present the general setup for a HOMER model and a simple extension of the algorithm that is suited for MLCs that output rankings. Furthermore, we provide a detailed analysis of the properties of the algorithm, both from an aspect of effectiveness and computational complexity. A secondary contribution involves the presentation of a balanced variant of the k means algorithm, which serves in the first step of the label hierarchy construction. We conduct extensive experiments on six real-world datasets, studying empirically HOMER's parameters and providing examples of instantiations of the algorithm with different clustering approaches and MLCs, The empirical results demonstrate a significant improvement over the given base MLC.
scikit-multilearn is a Python library for performing multi-label classification. The library is compatible with the scikit/scipy ecosystem and uses sparse matrices for all internal operations. It provides native Python implementations of popular multi-label classification methods alongside a novel framework for label space partitioning and division. It includes modern algorithm adaptation methods, network-based label space division approaches, which extracts label dependency information and multi-label embedding classifiers. It provides python wrapped access to the extensive multi-label method stack from Java libraries and makes it possible to extend deep learning single-label methods for multi-label tasks. The library allows multi-label stratification and data set management. The implementation is more efficient in problem transformation than other established libraries, has good test coverage and follows PEP8. Source code and documentation can be downloaded from http://scikit.ml and also via pip. The library follows BSD licensing scheme.
Multi-label classification is a type of supervised learning where an instance may belong to multiple labels simultaneously. Predicting each label independently has been criticized for not exploiting any correlation between labels. In this paper we propose a novel approach, Nearest Labelset using Double Distances (NLDD), that predicts the labelset observed in the training data that minimizes a weighted sum of the distances in both the feature space and the label space to the new instance. The weights specify the relative tradeoff between the two distances. The weights are estimated from a binomial regression of the number of misclassified labels as a function of the two distances. Model parameters are estimated by maximum likelihood. NLDD only considers labelsets observed in the training data, thus implicitly taking into account label dependencies. Experiments on benchmark multi-label data sets show that the proposed method on average outperforms other well-known approaches in terms of Hamming loss, 0/1 loss, and multi-label accuracy and ranks second after ECC on the F-measure.
We study the performance of data-driven, a priori and random approaches to label space partitioning for multi-label classification with a Gaussian Naive Bayes classifier. Experiments were performed on 12 benchmark data sets and evaluated on 5 established measures of classification quality: micro and macro averaged F1 score, Subset Accuracy and Hamming loss. Data-driven methods are significantly better than an average run of the random baseline. In case of F1 scores and Subset Accuracy - data driven approaches were more likely to perform better than random approaches than otherwise in the worst case. There always exists a method that performs better than a priori methods in the worst case. The advantage of data-driven methods against a priori methods with a weak classifier is lesser than when tree classifiers are used.
Label propagation is a powerful and flexible semi-supervised learning technique on graphs. Neural networks, on the other hand, have proven track records in many supervised learning tasks. In this work, we propose a training framework with a graph-regularised objective, namely "Neural Graph Machines", that can combine the power of neural networks and label propagation. This work generalises previous literature on graph-augmented training of neural networks, enabling it to be applied to multiple neural architectures (Feed-forward NNs, CNNs and LSTM RNNs) and a wide range of graphs. The new objective allows the neural networks to harness both labeled and unlabeled data by: (a) allowing the network to train using labeled data as in the supervised setting, (b) biasing the network to learn similar hidden representations for neighboring nodes on a graph, in the same vein as label propagation. Such architectures with the proposed objective can be trained efficiently using stochastic gradient descent and scaled to large graphs, with a runtime that is linear in the number of edges. The proposed joint training approach convincingly outperforms many existing methods on a wide range of tasks (multi-label classification on social graphs, news categorization, document classification and semantic intent classification), with multiple forms of graph inputs (including graphs with and without node-level features) and using different types of neural networks.
The multi-label classification framework, where each observation can be associated with a set of labels, has generated a tremendous amount of attention over recent years. The modern multi-label problems are typically large-scale in terms of number of observations, features and labels, and the amount of labels can even be comparable with the amount of observations. In this context, different remedies have been proposed to overcome the curse of dimensionality. In this work, we aim at exploiting the output sparsity by introducing a new loss, called the sparse weighted Hamming loss. This proposed loss can be seen as a weighted version of classical ones, where active and inactive labels are weighted separately. Leveraging the influence of sparsity in the loss function, we provide improved generalization bounds for the empirical risk minimizer, a suitable property for large-scale problems. For this new loss, we derive rates of convergence linear in the underlying output-sparsity rather than linear in the number of labels. In practice, minimizing the associated risk can be performed efficiently by using convex surrogates and modern convex optimization algorithms. We provide experiments on various real-world datasets demonstrating the pertinence of our approach when compared to non-weighted techniques.
In this paper, we propose a novel approach for learning multi-label classifiers with the help of privileged information. Specifically, we use similarity constraints to capture the relationship between available information and privileged information, and use ranking constraints to capture the dependencies among multiple labels. By integrating similarity constraints and ranking constraints into the learning process of classifiers, the privileged information and the dependencies among multiple labels are exploited to construct better classifiers during training. A maximum margin classifier is adopted, and an efficient learning algorithm of the proposed method is also developed. We evaluate the proposed method on two applications: multiple object recognition from images with the help of implicit information about object importance conveyed by the list of manually annotated image tags; and multiple facial action unit detection from low-resolution images augmented by high-resolution images. Experimental results demonstrate that the proposed method can effectively take full advantage of privileged information and dependencies among multiple labels for better object recognition and better facial action unit detection.
Artificial neural networks (ANNs) have gained a well-deserved popularity among machine learning tools upon their recent successful applications in image- and sound processing and classification problems. ANNs have also been applied for predicting the family or function of a protein, knowing its residue sequence. Here we present two new ANNs with multi-label classification ability, showing impressive accuracy when classifying protein sequences into 698 UniProt families (AUC=99.99%) and 983 Gene Ontology classes (AUC=99.45%).
Multi-label image classification is a fundamental but challenging task in computer vision. Great progress has been achieved by exploiting semantic relations between labels in recent years. However, conventional approaches are unable to model the underlying spatial relations between labels in multi-label images, because spatial annotations of the labels are generally not provided. In this paper, we propose a unified deep neural network that exploits both semantic and spatial relations between labels with only image-level supervisions. Given a multi-label image, our proposed Spatial Regularization Network (SRN) generates attention maps for all labels and captures the underlying relations between them via learnable convolutions. By aggregating the regularized classification results with original results by a ResNet-101 network, the classification performance can be consistently improved. The whole deep neural network is trained end-to-end with only image-level annotations, thus requires no additional efforts on image annotations. Extensive evaluations on 3 public datasets with different types of labels show that our approach significantly outperforms state-of-the-arts and has strong generalization capability. Analysis of the learned SRN model demonstrates that it can effectively capture both semantic and spatial relations of labels for improving classification performance.
This paper introduces a new large-scale music dataset, MusicNet, to serve as a source of supervision and evaluation of machine learning methods for music research. MusicNet consists of hundreds of freely-licensed classical music recordings by 10 composers, written for 11 instruments, together with instrument/note annotations resulting in over 1 million temporal labels on 34 hours of chamber music performances under various studio and microphone conditions. The paper defines a multi-label classification task to predict notes in musical recordings, along with an evaluation protocol, and benchmarks several machine learning architectures for this task: i) learning from spectrogram features; ii) end-to-end learning with a neural net; iii) end-to-end learning with a convolutional neural net. These experiments show that end-to-end models trained for note prediction learn frequency selective filters as a low-level representation of audio.
Multi-Label Classification toolbox is a MATLAB/OCTAVE library for Multi-Label Classification (MLC). There exists a few Java libraries for MLC, but no MATLAB/OCTAVE library that covers various methods. This toolbox offers an environment for evaluation, comparison and visualization of the MLC results. One attraction of this toolbox is that it enables us to try many combinations of feature space dimension reduction, sample clustering, label space dimension reduction and ensemble, etc.
We introduce a novel approach for estimating Latent Dirichlet Allocation (LDA) parameters from collapsed Gibbs samples (CGS), by leveraging the full conditional distributions over the latent variable assignments to efficiently average over multiple samples, for little more computational cost than drawing a single additional collapsed Gibbs sample. Our approach can be understood as adapting the soft clustering methodology of Collapsed Variational Bayes (CVB0) to CGS parameter estimation, in order to get the best of both techniques. Our estimators can straightforwardly be applied to the output of any existing implementation of CGS, including modern accelerated variants. We perform extensive empirical comparisons of our estimators with those of standard collapsed inference algorithms on real-world data for both unsupervised LDA and Prior-LDA, a supervised variant of LDA for multi-label classification. Our results show a consistent advantage of our approach over traditional CGS under all experimental conditions, and over CVB0 inference in the majority of conditions. More broadly, our results highlight the importance of averaging over multiple samples in LDA parameter estimation, and the use of efficient computational techniques to do so.
Background: In this paper we present the approaches and methods employed in order to deal with a large scale multi-label semantic indexing task of biomedical papers. This work was mainly implemented within the context of the BioASQ challenge of 2014. Methods: The main contribution of this work is a multi-label ensemble method that incorporates a McNemar statistical significance test in order to validate the combination of the constituent machine learning algorithms. Some secondary contributions include a study on the temporal aspects of the BioASQ corpus (observations apply also to the BioASQ's super-set, the PubMed articles collection) and the proper adaptation of the algorithms used to deal with this challenging classification task. Results: The ensemble method we developed is compared to other approaches in experimental scenarios with subsets of the BioASQ corpus giving positive results. During the BioASQ 2014 challenge we obtained the first place during the first batch and the third in the two following batches. Our success in the BioASQ challenge proved that a fully automated machine-learning approach, which does not implement any heuristics and rule-based approaches, can be highly competitive and outperform other approaches in similar challenging contexts.
Predicting the subcellular localization of proteins is an important and challenging problem. Traditional experimental approaches are often expensive and time-consuming. Consequently, a growing number of research efforts employ a series of machine learning approaches to predict the subcellular location of proteins. There are two main challenges among the state-of-the-art prediction methods. First, most of the existing techniques are designed to deal with multi-class rather than multi-label classification, which ignores connections between multiple labels. In reality, multiple locations of particular proteins implies that there are vital and unique biological significances that deserve special focus and cannot be ignored. Second, techniques for handling imbalanced data in multi-label classification problems are necessary, but never employed. For solving these two issues, we have developed an ensemble multi-label classifier called HPSLPred, which can be applied for multi-label classification with an imbalanced protein source. For convenience, a user-friendly webserver has been established at http://server.malab.cn/HPSLPred.