28 citations · 57 across the 8 of their papers we have counts for
5 papers · 1 filter
Representer Point Selection for Explaining Regularized High-dimensional Models
Che-Ping Tsai, Jiong Zhang, Eli Chien +3
We introduce a novel class of sample-based explanations we term high-dimensional representers, that can be used to explain the predictions of a regularized high-dimensional model i…
PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation
Eli Chien, Jiong Zhang, Cho-Jui Hsieh +4
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 extractio…
Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
Eli Chien, Wei-Cheng Chang, Cho-Jui Hsieh +4
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 nu…
Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification
Jiong Zhang, Wei-cheng Chang, Hsiang-fu Yu +1
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 formu…
PECOS: Prediction for Enormous and Correlated Output Spaces
Hsiang-Fu Yu, Kai Zhong, Jiong Zhang +2
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…