# The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis

arXiv: https://arxiv.org/abs/2009.07022 · HTML: https://mlsanity.com/paper/2009.07022/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2020.

## Built on by (most cited first, 10 of 10)

- [FedBABU: Towards Enhanced Representation for Federated Image Classification](https://mlsanity.com/paper/2106.06042/) (2021)
- [A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing](https://mlsanity.com/paper/2210.04675/) (2022)
- [Margin Calibration for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2112.07225/) (2021)
- [FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learning](https://mlsanity.com/paper/2311.13267/) (2023)
- [A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applications](https://mlsanity.com/paper/2403.01387/) (2024)
- [DELTA: Decoupling Long-Tailed Online Continual Learning](https://mlsanity.com/paper/2404.04476/) (2024)
- [Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction](https://mlsanity.com/paper/2104.00312/) (2021)
- [FedBug: A Bottom-Up Gradual Unfreezing Framework for Federated Learning](https://mlsanity.com/paper/2307.10317/) (2023)
- [Demystifying the Base and Novel Performances for Few-shot Class-incremental Learning](https://mlsanity.com/paper/2206.10596/) (2022)
- [Global Federated Learning Strategies for Building Efficient Personalized Models](https://mlsanity.com/paper/2608.15107/) (2026)

## Abstract (arXiv)

Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance. Existing solutions usually address this issue via class-balancing strategies, e.g., data re-sampling and loss re-weighting, but all these methods adhere to the schema of entangling learning of the representation and classifier. In this study, we conduct an in-depth empirical investigation into the long-tailed problem and found that pre-trained models with instance-balanced sampling already capture the well-learned representations for all classes; moreover, it is possible to achieve better long-tailed classification ability at low cost by only adjusting the classifier. Inspired by this observation, we propose a robust classifier with attentive relation routing, which assigns soft weights by automatically aggregating the relations. Extensive experiments on two datasets demonstrate the effectiveness of our proposed approach. Code and datasets are available in https://github.com/zjunlp/deepke.