DWGF
A Diffusion Weighted Graph Framework for New Intent Discovery
Install / Use
/learn @yibai-shi/DWGFREADME
DWGF
Code for the paper titled A Diffusion Weighted Graph Framework for New Intent Discovery
Contents
Data
We performed experiments on three public datasets: clinc, banking and stackoverflow, which have been included in our repository in the data folder ' ./data '.
Requirements
- python==3.8
- pytorch==1.12.0
- transformers==4.26.1
- scipy==1.10.1
- numpy==1.23.5
- scikit-learn==1.2.1
Running
Pre-training, training, and inference through the following scripts:
bash scripts/run_{dataset}.sh
Thanks
Some code references the following repositories:
Related Skills
node-connect
350.1kDiagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps
frontend-design
109.9kCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
openai-whisper-api
350.1kTranscribe audio via OpenAI Audio Transcriptions API (Whisper).
qqbot-media
350.1kQQBot 富媒体收发能力。使用 <qqmedia> 标签，系统根据文件扩展名自动识别类型（图片/语音/视频/文件）。
