Fast multi-resolution transformer fine-tuning for extreme multi-label text classification

J Zhang, WC Chang, HF Yu… - Advances in Neural …, 2021 - proceedings.neurips.cc
Extreme multi-label text classification~(XMC) seeks to find relevant labels from an extreme
large label collection for a given text input. Many real-world applications can be formulated …

Node feature extraction by self-supervised multi-scale neighborhood prediction

E Chien, WC Chang, CJ Hsieh, HF Yu, J Zhang… - arxiv preprint arxiv …, 2021 - arxiv.org
Learning on graphs has attracted significant attention in the learning community due to
numerous real-world applications. In particular, graph neural networks (GNNs), which take …

Multi-label feature selection via robust flexible sparse regularization

Y Li, L Hu, W Gao - Pattern Recognition, 2023 - Elsevier
Multi-label feature selection is an efficient technique to deal with the high dimensional multi-
label data by selecting the optimal feature subset. Existing researches have demonstrated …

Matryoshka representation learning

A Kusupati, G Bhatt, A Rege… - Advances in …, 2022 - proceedings.neurips.cc
Learned representations are a central component in modern ML systems, serving a
multitude of downstream tasks. When training such representations, it is often the case that …

Pecos: Prediction for enormous and correlated output spaces

HF Yu, K Zhong, J Zhang, WC Chang… - Journal of Machine …, 2022 - jmlr.org
Many large-scale applications amount to finding relevant results from an enormous output
space of potential candidates. For example, finding the best matching product from a large …

Cascadexml: Rethinking transformers for end-to-end multi-resolution training in extreme multi-label classification

S Kharbanda, A Banerjee… - Advances in neural …, 2022 - proceedings.neurips.cc
Abstract Extreme Multi-label Text Classification (XMC) involves learning a classifier that can
assign an input with a subset of most relevant labels from millions of label choices. Recent …

Extreme zero-shot learning for extreme text classification

Y **ong, WC Chang, CJ Hsieh, HF Yu… - arxiv preprint arxiv …, 2021 - arxiv.org
The eXtreme Multi-label text Classification (XMC) problem concerns finding most relevant
labels for an input text instance from a large label set. However, the XMC setup faces two …

Knowledge-aided momentum contrastive learning for remote-sensing image text retrieval

Z Ji, C Meng, Y Zhang, Y Pang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Remote-sensing image–text retrieval (RSITR) has attracted widespread attention due to its
great potential for rapid information mining ability on remote-sensing images. Although …

Pina: Leveraging side information in extreme multi-label classification via predicted instance neighborhood aggregation

E Chien, J Zhang, CJ Hsieh, JY Jiang… - arxiv preprint arxiv …, 2023 - arxiv.org
The eXtreme Multi-label Classification~(XMC) problem seeks to find relevant labels from an
exceptionally large label space. Most of the existing XMC learners focus on the extraction of …

Eliminate Before Align: A Remote Sensing Image-Text Retrieval Framework with Keyword Explicit Reasoning

Z Ji, C Meng, Y Zhang, H Wang, Y Pang… - Proceedings of the 32nd …, 2024 - dl.acm.org
Mountains of researches center around the Remote Sensing Image-Text Retrieval (RSITR),
aiming at retrieving the corresponding targets based on the given query. Among them, the …