PyData Berlin 2024 February Meetup

Welcome to the wonderful February of Pydata Berlin meetup!

We would like to welcome you all starting from 18:45. The talks begin around 19.15.

Please provide your first and last name for the registration because this is required for the venue's entry policy. If you cannot attend, please cancel your spot so others are able to join as the space is limited.

**************************************************************************
The Lineup for the Evening

Talk 1: Exploiting Data Structure and Geometry with a Diffusion-based Graph Neural Network

Abstract: Exploiting the problem's underlying structure can help improve the performance of deep learning models. This is in particular true for applications that deal with graphs, where graph neural networks have often become the state-of-the-art. In this talk, I will introduce a novel graph neural network based on diffusion in manifolds and explain how it can exploit several common characteristics of learning problems on graphs for better results. In particular, I will discuss how its invariance/equivariance properties can boost performance. The network can handle node features from general Riemannian manifolds, which opens up a broad spectrum of possible applications.

Speaker: Dr. Martin Hanik

Talk 2: Instructions Fine-tuning using Alpaca: Lessons Learned and Practical Considerations

Abstract: Large language models became the workhorse for natural language processing tasks. By formulating a task definition in a prompt, LLMs such as Alpaca achieve state-of-the-art effectiveness on many NLP tasks (e.g., Sentiment Analysis). In this presentation, I will explain the difference between instruction fine-tuning, prompting, and prompt tuning. Then, I will present a use case for fine-tuning Alpaca on Sentiment Analysis and compare it with prompting. Finally, I will present lessons learned for formulating the instructions and instruction fine-tuning using Alpaca.

Speaker: Yamen Ajjour is a postdoctoral researcher at Leibniz University Hannover. At the Institute for Artificial Intelligence, he is doing research on argument generation and Large Language Models. In his Ph.D. time in Weimar, Yamen worked with other researchers on developing the first argument search engine, which retrieves pro and con arguments for a given controversial topic. Yamen was awarded the Best Paper Award at the German Conference for Artificial Intelligence in 2019.

There will be slots for 2-3 Lightning Talks (5-6 Minutes for each).
Kindly let us know if you would like to present something at the start of the meetup :)

***
NumFOCUS Code of Conduct
THE SHORT VERSION
Be kind to others. Do not insult or put down others. Behave professionally. Remember that harassment and sexist, racist, or exclusionary jokes are not appropriate for NumFOCUS.
All communication should be appropriate for a professional audience including people of many different backgrounds. Sexual language and imagery are not appropriate.
NumFOCUS is dedicated to providing a harassment-free community for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of community members in any form.
Thank you for helping make this a welcoming, friendly community for all.
If you haven't yet, please read the detailed version here: https://numfocus.org/code-of-conduct
***
HOSTS:
GetYourGuide is the best place to unlock unforgettable travel experiences all over the world. See our open positions on careers.getyourguide.com or get a behind-the-scenes look at life at GetYourGuide on our blog: inside.getyourguide.com.