Extreme multi-label learning (XML) or classification has been a practical and important problem since the boom of big data. The main challenge lies in the exponential label space which involves 2 possible label sets when the label dimension L is very large, e.g., in millions for Wikipedia labels. This paper is motivated to better explore the label space by building and modeling an explicit labe...

Graph embedding learns low-dimensional representations for nodes or edges on the graph, which is widely applied in many real-world applications. Excessive graph mining promotes research of attack methods embedding. Most generate perturbations that maximize deviation prediction confidence. They are difficult to accurately misclassify instances into target label, and nonminimized more easily dete...

Automatically tagging textual mentions with the concepts, types and entities that they represent are important tasks for which supervised learning has been found to be very effective. In this paper, we consider the problem of exploiting multiple sources of training data with variant ontologies. We present a new transfer learning approach based on embedding multiple label sets in a shared space,...

This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem. Specifically, most existing ZSL methods focus on learning mapping functions from the image feature space to the label embedding space. Whereas, the proposed method explores a simple yet effective transductive framework in the reverse way – our method estim...

The objective in extreme multi-label learning is to train a classifier that can automatically tag a novel data point with the most relevant subset of labels from an extremely large label set. Embedding based approaches make training and prediction tractable by assuming that the training label matrix is low-rank and hence the effective number of labels can be reduced by projecting the high dimen...

Multi-task learning in text classification leverages implicit correlations among related tasks to extract common features and yield performance gains. However, most previous works treat labels of each task as independent and meaningless onehot vectors, which cause a loss of potential information and makes it difficult for these models to jointly learn three or more tasks. In this paper, we prop...

The objective in extreme multi-label learning is to train a classifier that can automatically tag a novel data point with the most relevant subset of labels from an extremely large label set. Embedding based approaches attempt to make training and prediction tractable by assuming that the training label matrix is low-rank and reducing the effective number of labels by projecting the high dimens...

Recent advances in language modeling such as word2vec motivate a number of graph embedding approaches by treating random walk sequences as sentences to encode structural proximity in a graph. However, most of the existing principles of neural graph embedding do not incorporate auxiliary information such as node content flexibly. In this paper we take a matrix factorization perspective of graph ...