Multi-label learning studies the problem where each example is represented by a single instance while associated with a set of labels simultaneously. During the past decade, significant amount of progresses have been made toward this emerging machine learning paradigm. This paper aims to provide a timely review on this area with emphasis on state-of-the-art multi-label learning algorithms. Firstly, fundamentals on multi-label learning including formal definition and evaluation metrics are given. Secondly and primarily, eight representative multi-label learning algorithms are scrutinized under common notations with relevant analyses and discussions. Thirdly, several related learning settings are briefly summarized. As a conclusion, online resources and open research problems on multi-label learning are outlined for reference purposes.

https://romisatriawahono.net/lecture/rm/survey/machine%20learning/Zhang%20-%20Multi-Label%20Learning%20Algorithms%20-%202013.pdf

A Review On Multi-Label Learning Algorithms

Concept drift primarily refers to an online supervised learning scenario when the relation between the input data and the target variable changes over time. Assuming a general knowledge of supervised learning in this article, we characterize adaptive learning processes; categorize existing strategies for handling concept drift; overview the most representative, distinct, and popular techniques and algorithms; discuss evaluation methodology of adaptive algorithms; and present a set of illustrative applications. The survey covers the different facets of concept drift in an integrated way to reflect on the existing scattered state of the art. Thus, it aims at providing a comprehensive introduction to the concept drift adaptation for researchers, industry analysts, and practitioners.

/pdf/a-survey-on-concept-drift-adaptation-xv7b4z5tkr.pdf

A survey on concept drift adaptation

Among available genome relatedness indices, average nucleotide identity (ANI) is one of the most robust measurements of genomic relatedness between strains, and has great potential in the taxonomy of bacteria and archaea as a substitute for the labour-intensive DNA–DNA hybridization (DDH) technique. An ANI threshold range (95–96 %) for species demarcation had previously been suggested based on comparative investigation between DDH and ANI values, albeit with rather limited datasets. Furthermore, its generality was not tested on all lineages of prokaryotes. Here, we investigated the overall distribution of ANI values generated by pairwise comparison of 6787 genomes of prokaryotes belonging to 22 phyla to see whether the suggested range can be applied to all species. There was an apparent distinction in the overall ANI distribution between intra- and interspecies relationships at around 95–96 % ANI. We went on to determine which level of 16S rRNA gene sequence similarity corresponds to the currently accepted ANI threshold for species demarcation using over one million comparisons. A twofold cross-validation statistical test revealed that 98.65 % 16S rRNA gene sequence similarity can be used as the threshold for differentiating two species, which is consistent with previous suggestions (98.2–99.0 %) derived from comparative studies between DDH and 16S rRNA gene sequence similarity. Our findings should be useful in accelerating the use of genomic sequence data in the taxonomy of bacteria and archaea.

Towards a taxonomic coherence between average nucleotide identity and 16S rRNA gene sequence similarity for species demarcation of prokaryotes

The widely known binary relevance method for multi-label classification, which considers each label as an independent binary problem, has often been overlooked in the literature due to the perceived inadequacy of not directly modelling label correlations. Most current methods invest considerable complexity to model interdependencies between labels. This paper shows that binary relevance-based methods have much to offer, and that high predictive performance can be obtained without impeding scalability to large datasets. We exemplify this with a novel classifier chains method that can model label correlations while maintaining acceptable computational complexity. We extend this approach further in an ensemble framework. An extensive empirical evaluation covers a broad range of multi-label datasets with a variety of evaluation metrics. The results illustrate the competitiveness of the chaining method against related and state-of-the-art methods, both in terms of predictive performance and time complexity.

/pdf/classifier-chains-for-multi-label-classification-2zqb5tuej1.pdf

Classifier chains for multi-label classification

Ensemble methods are considered the state‐of‐the art solution for many machine learning challenges. Such methods improve the predictive performance of a single model by training multiple models and combining their predictions. This paper introduce the concept of ensemble learning, reviews traditional, novel and state‐of‐the‐art ensemble methods and discusses current challenges and trends in the field.

Ensemble learning: A survey

Massive Online Analysis (MOA) is a software environment for implementing algorithms and running experiments for online learning from evolving data streams MOA includes a collection of offline and online methods as well as tools for evaluation In particular, it implements boosting, bagging, and Hoeffding Trees, all with and without Naive Bayes classifiers at the leaves MOA supports bi-directional interaction with WEKA, the Waikato Environment for Knowledge Analysis, and is released under the GNU GPL license

/pdf/moa-massive-online-analysis-21e9i6edk1.pdf

MOA: Massive Online Analysis

The widely known binary relevance method for multi-label classification, which considers each label as an independent binary problem, has been sidelined in the literature due to the perceived inadequacy of its label-independence assumption. Instead, most current methods invest considerable complexity to model interdependencies between labels. This paper shows that binary relevance-based methods have much to offer, especially in terms of scalability to large datasets. We exemplify this with a novel chaining method that can model label correlations while maintaining acceptable computational complexity. Empirical evaluation over a broad range of multi-label datasets with a variety of evaluation metrics demonstrates the competitiveness of our chaining method against related and state-of-the-art methods, both in terms of predictive performance and time complexity.

/pdf/classifier-chains-for-multi-label-classification-1o36dx5mgx.pdf

Classifier Chains for Multi-label Classification

Advanced analysis of data streams is quickly becoming a key area of data mining research as the number of applications demanding such processing increases. Online mining when such data streams evolve over time, that is when concepts drift or change completely, is becoming one of the core issues. When tackling non-stationary concepts, ensembles of classifiers have several advantages over single classifier methods: they are easy to scale and parallelize, they can adapt to change quickly by pruning under-performing parts of the ensemble, and they therefore usually also generate more accurate concept descriptions. This paper proposes a new experimental data stream framework for studying concept drift, and two new variants of Bagging: ADWIN Bagging and Adaptive-Size Hoeffding Tree (ASHT) Bagging. Using the new experimental framework, an evaluation study on synthetic and real-world datasets comprising up to ten million examples shows that the new ensemble methods perform very well compared to several known methods.

/pdf/new-ensemble-methods-for-evolving-data-streams-p1gdf0uj61.pdf

New ensemble methods for evolving data streams

Random forests is currently one of the most used machine learning algorithms in the non-streaming (batch) setting. This preference is attributable to its high learning performance and low demands with respect to input preparation and hyper-parameter tuning. However, in the challenging context of evolving data streams, there is no random forests algorithm that can be considered state-of-the-art in comparison to bagging and boosting based algorithms. In this work, we present the adaptive random forest (ARF) algorithm for classification of evolving data streams. In contrast to previous attempts of replicating random forests for data stream learning, ARF includes an effective resampling method and adaptive operators that can cope with different types of concept drifts without complex optimizations for different data sets. We present experiments with a parallel implementation of ARF which has no degradation in terms of classification performance in comparison to a serial implementation, since trees and adaptive operators are independent from one another. Finally, we compare ARF with state-of-the-art algorithms in a traditional test-then-train evaluation and a novel delayed labelling evaluation, and show that ARF is accurate and uses a feasible amount of resources.

/pdf/adaptive-random-forests-for-evolving-data-stream-edive352ue.pdf

Geoff Holmes

Papers

Classifier chains for multi-label classification

MOA: Massive Online Analysis

Classifier Chains for Multi-label Classification

New ensemble methods for evolving data streams

Adaptive random forests for evolving data stream classification