Inconsistent Node Flattening for Improving Top-Down Hierarchical Classification

Abstract

Large-scale classification of data where classes are structurally organized in a hierarchy is an important area of research. Top-down approaches that exploit the hierarchy during the learning and prediction phase are efficient for largescale hierarchical classification. However, accuracy of top-down approaches is poor due to error propagation i.e., prediction errors made at higher levels in the hierarchy cannot be corrected at lower levels. One of the main reason behind errors at the higher levels is the presence of inconsistent nodes that are introduced due to the arbitrary process of creating these hierarchies by domain experts. In this paper, we propose two different data-driven approaches (local and global) for hierarchical structure modification that identifies and flattens inconsistent nodes present within the hierarchy. Our extensive empirical evaluation of the proposed approaches on several image and text datasets with varying distribution of features, classes and training instances per class shows improved classification performance over competing hierarchical modification approaches. Specifically, we see an improvement upto 7% in Macro-F1 score with our approach over best TD baseline. SOURCE CODE:

Review on hierarchical learning methods for large-scale classification task

“…其次, 已有层次结构调整. 对于给定的层次结构, 如何度量其与特征空间的不一致性以进行结构 调整是一个重要的问题, 但是目前只有少数工作关注这个方向 [77∼79] , 其中大多是启发式的方法 [78,79] , 无法给出其有效性的理论证明和有效适用的场景. 利用数学理论对不同分类任务进行结构调整, 对分 层分类的错误传播问题和实际应用有着极为重要的意义.…”

HierFlat: flattened hierarchies for improving top-down hierarchical classification

“…To validate the performance improvement, we conducted pairwise statistical significance tests between our best approach, Global-INF and best top-down baseline for all datasets except DMOZ-2010 and DMOZ-2012, where true test labels (and class-wise performance) are not available from the online evaluation. Specifically, we compute sign test for μF 1 [38] and nonparametric Wilcoxon rank test for MF 1 scores (it should be noted that significance tests are between two approaches for single run). In Fig.…”

“…Performance based on hierarchical metrics: Hierarchical evaluation metrics hF 1 and TE compute errors for misclassified examples based on the definition of a defined hierarchy. Table 6 (Table 7) shows the hF 1 and TE score for all topdown approaches evaluated over the original hierarchy and the modified hierarchy (obtained by flattening). We can see that our proposed approach, Global-INF outperforms other approaches because it is able to identify a better set of inconsistent nodes.…”

“…Hierarchies (taxonomies) are the most common and useful data structures for organizing large volume of datasets in various application domains including bioinformatics 1 for organizing gene sequences, ImageNet 2 for organizing images and Yahoo! 3 web directories for organizing web documents.…”

Embedding feature selection for large-scale hierarchical classification

“…Several methods have been developed to address the hierarchical classification problem [4,5,10,11,12]. These methods can be broadly divided into three major categories.…”