Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning (2110.08254v1)

Published 13 Oct 2021 in cs.LG and cs.CL

Abstract: Standard few-shot relation classification (RC) is designed to learn a robust classifier with only few labeled data for each class. However, previous works rarely investigate the effects of a different number of classes (i.e., $N$-way) and number of labeled data per class (i.e., $K$-shot) during training vs. testing. In this work, we define a new task, \textit{inconsistent few-shot RC}, where the model needs to handle the inconsistency of $N$ and $K$ between training and testing. To address this new task, we propose Prototype Network-based cross-attention contrastive learning (ProtoCACL) to capture the rich mutual interactions between the support set and query set. Experimental results demonstrate that our ProtoCACL can outperform the state-of-the-art baseline model under both inconsistent $K$ and inconsistent $N$ settings, owing to its more robust and discriminate representations. Moreover, we identify that in the inconsistent few-shot learning setting, models can achieve better performance with \textit{less data} than the standard few-shot setting with carefully-selected $N$ and $K$. In the end of the paper, we provide further analyses and suggestions to systematically guide the selection of $N$ and $K$ under different scenarios.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Hongru Wang (62 papers)
  2. Zhijing Jin (68 papers)
  3. Jiarun Cao (4 papers)
  4. Gabriel Pui Cheong Fung (5 papers)
  5. Kam-Fai Wong (92 papers)
Citations (3)

Summary

We haven't generated a summary for this paper yet.