Related papers: Utilizing Local Hierarchy with Adversarial Trainin…

Recent studies have shown that attackers can catastrophically reduce the performance of GNNs by maliciously modifying the graph structure or node features on the graph. Adversarial training, which has been shown to be one of the most…

In recent years, simultaneous learning of multiple dense prediction tasks with partially annotated label data has emerged as an important research area. Previous works primarily focus on leveraging cross-task relations or conducting…

Network alignment task, which aims to identify corresponding nodes in different networks, is of great significance for many subsequent applications. Without the need for labeled anchor links, unsupervised alignment methods have been…

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…

Large-scale Multi-label Text Classification (LMTC) has a wide range of Natural Language Processing (NLP) applications and presents interesting challenges. First, not all labels are well represented in the training set, due to the very large…

This work proposes a novel approach to the deep hierarchical classification task, i.e., the problem of classifying data according to multiple labels organized in a rigid parent-child structure. It consists in a multi-output deep neural…

Cognitive diagnosis (CD) aims to reveal students' proficiency in specific knowledge concepts. With the increasing adoption of intelligent education applications, accurately assessing students' knowledge mastery has become an urgent…

In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally…

Human data labeling is an important and expensive task at the heart of supervised learning systems. Hierarchies help humans understand and organize concepts. We ask whether and how concept hierarchies can inform the design of annotation…

ICD(International Classification of Diseases) coding involves assigning ICD codes to patients visit based on their medical notes. ICD coding is a challenging multilabel text classification problem due to noisy medical document inputs.…

We introduce HTAD, a novel model for diagnosis prediction using Electronic Health Records (EHR) represented as Heterogeneous Information Networks. Recent studies on modeling EHR have shown success in automatically learning representations…

We consider the problem of multi-label classification where the labels lie in a hierarchy. However, unlike most existing works in hierarchical multi-label classification, we do not assume that the label-hierarchy is known. Encouraged by the…

Hierarchical classification (HC) assigns each object with multiple labels organized into a hierarchical structure. The existing deep learning based HC methods usually predict an instance starting from the root node until a leaf node is…

Classification algorithms in machine learning often assume a flat label space. However, most real world data have dependencies between the labels, which can often be captured by using a hierarchy. Utilizing this relation can help develop a…

The advent of Large Language Models (LLMs) has provided unprecedented capabilities for analyzing unstructured text data. However, deploying these models as reliable, robust, and scalable classifiers in production environments presents…

The self-supervised ultrasound (US) video model pretraining can use a small amount of labeled data to achieve one of the most promising results on US diagnosis. However, it does not take full advantage of multi-level knowledge for learning…

Human beings learn and accumulate hierarchical knowledge over their lifetime. This knowledge is associated with previous concepts for consolidation and hierarchical construction. However, current incremental learning methods lack the…

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…

State-of-the-art approaches to spelling error correction problem include Transformer-based Seq2Seq models, which require large training sets and suffer from slow inference time; and sequence labeling models based on Transformer encoders…

A great variety of text tasks such as topic or spam identification, user profiling, and sentiment analysis can be posed as a supervised learning problem and tackle using a text classifier. A text classifier consists of several subprocesses,…