Related papers: Filter based Taxonomy Modification for Improving H…
In applications where categorical labels follow a natural hierarchy, classification methods that exploit the label structure often outperform those that do not. Un-fortunately, the majority of classification datasets do not come…
Practitioners from many disciplines (e.g., political science) use expert-crafted taxonomies to make sense of large, unlabeled corpora. In this work, we study Seeded Hierarchical Clustering (SHC): the task of automatically fitting unlabeled…
The hierarchical structure inherent in many real-world datasets makes the modeling of such hierarchies a crucial objective in both unsupervised and supervised machine learning. While recent advancements have introduced deep architectures…
Hierarchical open-set classification handles previously unseen classes by assigning them to the most appropriate high-level category in a class taxonomy. We extend this paradigm to the semi-supervised setting, enabling the use of…
Taxonomy is a hierarchically structured knowledge graph that plays a crucial role in machine intelligence. The taxonomy expansion task aims to find a position for a new term in an existing taxonomy to capture the emerging knowledge in the…
In hierarchical text classification, we perform a sequence of inference steps to predict the category of a document from top to bottom of a given class taxonomy. Most of the studies have focused on developing novels neural network…
Real-world vision based applications require fine-grained classification for various area of interest like e-commerce, mobile applications, warehouse management, etc. where reducing the severity of mistakes and improving the classification…
Hierarchical text classification (HTC) is the task of assigning labels to a text within a structured space organized as a hierarchy. Recent works treat HTC as a conventional multilabel classification problem, therefore evaluating it as…
Hierarchical Instruction Following (HIF) refers to the problem of prompting large language models with a priority-ordered stack of instructions. Standard methods like RLHF and DPO typically fail in this problem since they mainly optimize…
Information retrieval is a core component of many intelligent systems as it enables conditioning of outputs on new and large-scale datasets. While effective, the standard practice of encoding data into high-dimensional representations for…
Tool learning aims to extend the capabilities of large language models (LLMs) with external tools. A major challenge in tool learning is how to support a large number of tools, including unseen tools. To address this challenge, previous…
We propose a hierarchical architecture for efficiently computing high-quality solutions to structured mixed-integer programs (MIPs). To reduce computational effort, our approach decouples the original problem into a higher level problem and…
Traditional classifiers treat all labels as mutually independent, thereby considering all negative classes to be equally incorrect. This approach fails severely in many real-world scenarios, where a known semantic hierarchy defines a…
We investigate the problem of reducing mistake severity for fine-grained classification. Fine-grained classification can be challenging, mainly due to the requirement of domain expertise for accurate annotation. However, humans are…
We consider the problem of unsupervised skill segmentation and hierarchical structure discovery in reinforcement learning. While recent approaches have sought to segment trajectories into reusable skills or options, most rely on action…
Semi-supervised learning approaches have emerged as an active area of research to combat the challenge of obtaining large amounts of annotated data. Towards the goal of improving the performance of semi-supervised learning methods, we…
Online educational platforms organize academic questions based on a hierarchical learning taxonomy (subject-chapter-topic). Automatically tagging new questions with existing taxonomy will help organize these questions into different classes…
Supervision for metric learning has long been given in the form of equivalence between human-labeled classes. Although this type of supervision has been a basis of metric learning for decades, we argue that it hinders further advances in…
We investigate the scalable image classification problem with a large number of categories. Hierarchical visual data structures are helpful for improving the efficiency and performance of large-scale multi-class classification. We propose a…
Regression tasks in computer vision, such as age estimation or counting, are often formulated into classification by quantizing the target space into classes. Yet real-world data is often imbalanced -- the majority of training samples lie…