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.
RESEARCH
-
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 -
Immune Engineering: CAR-T and Genomics Revolutionize Disease Treatment
By
–
“I’ve become convinced that immune engineering is one of the most promising frontiers for the application of the 4-S stack.” A brilliant one on CAR-T, genomics, and engineering immune cells to cure every disease. https://
open.substack.com/pub/centuryofb
io/p/immune-engineering
… -
New Programming Paradigm Expands Developer Base to 1.5B People
By
–
This is not an exhaustive list (people can add more in replies), but at least some of the articles I saw recently that stood out. It's still early days but this new programming paradigm has the potential to expand the number of programmers to ~1.5B people.
-
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. -
Prompting GPTs: Ask for the performance you want
By
–
3/ These two articles/papers: [1] https://
evjang.com/2021/10/23/gen
eralization.html
… [2] https://
arxiv.org/abs/2106.01345 bit more technical but TLDR good prompts include the desired/aspiring performance. GPTs don't "want" to succeed. They want to imitate. You want to succeed, and you have to ask for it. -
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 -
Media Coverage Gap: Views Versus Structural AI Shifts
By
–
The fundamental problem with journalism & media in a nutshell is: what generates views != what really matters it’s hard to blame the media for producing what makes them money (politics & personality pieces), but now it’s rare to read about structural shifts that really matter
-
AI Glossary: Overfitting, Underfitting, Bias and Variance Explained
By
–
In this @Cognilytica #AIToday #podcast AI Glossary Series episode 'Overfitting, Underfitting, Bias, Variance, Bias/Variance Tradeoff' hosts @rschmelzer & @kath0134 define these terms & explain how they relate to #AI. Full episode: https://
aidatatoday.com/ai-today-podca
st-ai-glossary-series-overfitting-underfitting-bias-variance-bias-variance-tradeoff/?utm_source=dlvr.it&utm_medium=twitter
…
#tech #data #bias #ML -
OODA Intelligence Analysis Master Class Video Playlist
By
–
The OODAcast videos on this playlist include interviews with great icons of intelligence analysis. Watching is like having a free master class in the art and craft of analysis: https://
youtube.com/playlist?list=
PL7VKU1kYSe_5yF411iShE-INE7dlPD0cw
… #OODA #analysis #risk