On Learning Vector Representations in Hierarchical Label Spaces
نویسندگان
چکیده
An important problem in multi-label classification is to capture label patterns or underlying structures that have an impact on such patterns. This paper addresses one such problem, namely how to exploit hierarchical structures over labels. We present a novel method to learn vector representations of a label space given a hierarchy of labels and label co-occurrence patterns. Our experimental results demonstrate qualitatively that the proposed method is able to learn regularities among labels by exploiting a label hierarchy as well as label co-occurrences. It highlights the importance of the hierarchical information in order to obtain regularities which facilitate analogical reasoning over a label space. We also experimentally illustrate the dependency of the learned representations on the label hierarchy.
منابع مشابه
Hierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents
This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...
متن کاملPredicting Unseen Labels Using Label Hierarchies in Large-Scale Multi-label Learning
An important problem in multi-label classification is to capture label patterns or underlying structures that have an impact on such patterns. One way of learning underlying structures over labels is to project both instances and labels into the same space where an instance and its relevant labels tend to have similar representations. In this paper, we present a novel method to learn a joint sp...
متن کاملPoincaré Embeddings for Learning Hierarchical Representations
Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs. However, while complex symbolic datasets often exhibit a latent hierarchical structure, state-of-the-art methods typically learn embeddings in Euclidean vector spaces, which do not account for this property. For this purpose, we introduce a new approach for learning hierarchical re...
متن کاملAbstract of " Discriminative Methods for Label Sequence Learning " Ii Discriminative Methods for Label Sequence Learning
of “Discriminative Methods for Label Sequence Learning” by Yasemin Altun, Ph.D., Brown University, May 2005. Discriminative learning framework is one of the very successful fields of machine learning. The methods of this paradigm, such as Boosting and Support Vector Machines, have significantly advanced the state-of-the-art for classification by improving the accuracy and by increasing the appl...
متن کاملOnline Learning for Object Recognition with a Hierarchical Visual Cortex Model
We present an architecture for the online learning of object representations based on a visual cortex hierarchy developed earlier. We use the output of a topographical feature hierarchy to provide a viewbased representation of three-dimensional objects as a form of visual short term memory. Objects are represented in an incremental vector quantization model, that selects and stores representati...
متن کامل