It only uses the learnable prompt vector and not the GNN weights, which are frozen for downstream tasks. This reduces the number of parameters that need to be updated, improves the computational efficiency of task learning/inference, and reduces the reliance on labeled data.
MACHINE LEARNING
-
Prompt Tuning Optimizes Downstream Task Efficiency and Accuracy
By
–
Prompt tuning involves optimizing the learnable prompt to improve the computational efficiency and accuracy of downstream tasks. It is based on the similarity of subgraphs and is formulated using prompt-assisted task-specific subgraph representations.
-
Learnable Prompts Enable Better Task-Specific Knowledge Extraction
By
–
Learnable prompts provide a better alternative to handcrafted prompts, and enable the extraction of the most relevant prior knowledge for each task. The prompts are a dimension-wise reweighting (or a linear transformation) of the node representations.
-
Graph Neural Networks Pre-training with Link Prediction Task
By
–
During pre-training, the GNN is trained on a link prediction task. By sampling nodes and forming triplets, a pre-training loss is constructed that improves the similarity between the contextual subgraphs of two candidate nodes.
-
GraphPrompt: Unified Pre-Training Framework for Graph Neural Networks
By
–
GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks Interesting pre-training training framework for GNNs, based on learnable prompts. It reduces labeling needs and boosts downstream task performance. https://
arxiv.org/abs/2302.08043 -
Prompts Enable Complex Multi-Step Reasoning Through Strategic Design
By
–
2/ These two [1] https://
arxiv.org/abs/2205.11916 , [2] https://
arxiv.org/abs/2211.01910 are good examples that the prompt can further program the "solution strategy", and with a good enough design of it, a lot more complex multi-step reasoning tasks become possible. -
LLMs In-Context Learning and Prompt Programming Capabilities
By
–
This tweet went wide, thought I'd post some of the recent supporting articles that inspired it.
1/ GPT-3 paper showed that LLMs perform in-context learning, and can be "programmed" inside the prompt with input:output examples to perform diverse tasks https://
arxiv.org/abs/2005.14165 -
Gradio: Fast Web Interface for ML Models Demo
By
–
2. Gradio → http://
gradio.app An alternative tool for making web apps for data science and machine learning. This is also a fastest way to demo your machine learning model with a friendly web interface. -
Streamlit: Open-source Python library for ML web apps
By
–
1. Streamlit → https://t.co/Qq4k2f72Ae
— Sumanth (@Sumanth_077) 19 février 2023
An open-source Python library that makes it easy to create and share web apps for machine learning and data science.
Just a few lines of code allows you to make beautiful demos of data scripts and ML models that you can share. pic.twitter.com/UBepd28ijI1. Streamlit → http://
streamlit.io An open-source Python library that makes it easy to create and share web apps for machine learning and data science. Just a few lines of code allows you to make beautiful demos of data scripts and ML models that you can share. -
3 Easiest Ways to Showcase Your Machine Learning Model
By
–
In Machine Learning after you train a model, the BEST way to showcase is it to make a demo for others to try it. Here are 3 of the easiest ways to make a demo of your machine-learning model: