Research map / Label-efficient and robust learning / Recognition and long-tail
Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Fine-tune XLNet-Base with the APLC output layer | XMTC classification · EURLex-4k | P@1: 87.14 -> 87.72 | Helped |
| Fine-tune XLNet-Base with the APLC output layer | XMTC classification · AmazonCat-13k | P@1: 93.55 -> 94.56 | Helped |
| Fine-tune XLNet-Base with the APLC output layer | XMTC classification · Wiki10-31k | P@1: 86.50 -> 89.44 | Helped |
| Fine-tune XLNet-Base with the APLC output layer | XMTC classification · Wiki-500k | P@1: 72.62 -> 72.83 | Helped |
| Fine-tune XLNet-Base with the APLC output layer | XMTC classification · Amazon-670k | P@1: 45.50 -> 43.46 | Hurt |
| Increase the number of evenly sized clusters (ablation) | APLC-XLNet · EURLex-4k | P@1: 87.72 -> 85.72 | Hurt |
| Increase the number of evenly sized clusters (ablation) | APLC-XLNet · Wiki10-31k | P@1 | Hurt |
| Allocate a larger proportion of labels to the head cluster rather than the last tail cluster (ablation) | APLC-XLNet · EURLex-4k and Wiki10-31k | P@1 | Helped |
| Use discriminative learning rates instead of one learning rate for the whole model (ablation) | APLC-XLNet · XMTC training | training effectiveness | Helped |
Closest papers by meaning
- AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification (NeurIPS 2019 · similarity 0.87)
- Harnessing the Power of Beta Scoring in Deep Active Learning for Multi-Label Text Classification (AAAI 2024 · similarity 0.84)
- ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces (ICML 2025 · similarity 0.84)
- Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification (AAAI 2024 · similarity 0.83)
- Compositional Generalization for Multi-Label Text Classification: A Data-Augmentation Approach (AAAI 2024 · similarity 0.83)
- Enhancing Multi-Label Classification via Dynamic Label-Order Learning (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.