Data Science Club


Гео и язык канала: не указан, не указан
Категория: не указана



Гео и язык канала
не указан, не указан
Категория
не указана
Статистика
Фильтр публикаций


Plug and Play Language Models: a Simple Approach to Controlled Text Generation
#gpt #nlp
PPLM allows a user to flexibly plug in one or more tiny attribute models representing the desired steering objective into a large, unconditional language model (LM). The method has the key property that it uses the LM as is—no training or fine-tuning is required—which enables researchers to leverage best-in-class LMs even if they do not have the extensive hardware required to train them.
Collab
https://colab.research.google.com/drive/1Ux0Z4-ruiVtJ6jUk98uk6FqfvGHCOYL3#scrollTo=W5UCitCoVLZC
Git
https://github.com/uber-research/PPLM


Правила для публикаций
1) Название в Болде(cntrl\command+B)
2)Хэштеги #sota #nlp #transformers #bert #gpt #data #dataset #opendata #edu #oth(other)
3) Enter между заголовком и описанием.
4) Описание - пара слов на русском/английском что это за модель
5)Рекомендуется добавить ссылку на коллаб ноутбук/веб версию.






Репост из: Graph Machine Learning
Fresh picks from ArXiv
This week on ArXiv: 2 surveys on self-supervised graph learning, fair embeddings, and combined structural and positional node embeddings 🎭

If I forgot to mention your paper, please shoot me a message and I will update the post.

Survey
* Graph Self-Supervised Learning: A Survey with Philip S. Yu
* Graph-based Semi-supervised Learning: A Comprehensive Review
* Meta-Learning with Graph Neural Networks: Methods and Applications
* Benchmarking Graph Neural Networks on Link Prediction
* A Survey of RDF Stores & SPARQL Engines for Querying Knowledge Graphs

Embeddings
* Towards a Unified Framework for Fair and Stable Graph Representation Learning with Marinka Zitnik
* Node Proximity Is All You Need: Unified Structural and Positional Node and Graph Embedding with Danai Koutra








Graph database

Язык для графовых баз данных, есть ноды, связи(edges), атрибуты - что то вроде свойства, класса.

В сэндбоксе есть пример работы с тролями в Твиттере.

https://neo4j.com/sandbox/

Пухтон апи
https://neo4j.com/developer/python/




Репост из: Graph Machine Learning
The Transformer Network for the Traveling Salesman Problem

(video and slides) Another great tutorial from Xavier Bresson on traveling salesman problem (TSP) and recent ML approaches to solve it. It gives a nice overview of the current solvers such as Concorde or Gurobi and their computational complexity.
Xavier Bresson:
Xavier Bresson - Nanyang Technological University, Singapore The Traveling Salesman Problem (TSP) is the most popular and most studied combinatorial problem, starting with von Neumann in 1951. It has driven the discovery of several optimization techniques such as cutting planes, branch-and-bound, lo...




Репост из: Библиотека data scientist’а | Data Science, Machine learning, анализ данных, машинное обучение
metaflow: с легкостью создавайте реальные проекты в области науки о данных и управляйте ими.

https://proglib.io/w/d8ec381f


Репост из: Graph Machine Learning
The Easiest Unsolved Problem in Graph Theory

Our new blog post about reconstruction conjecture, a well-known graph theory problem with 80 years of results but no final proof yet. I have already written several posts in this channel about it and it to me it's one of the grand challenges in graph theory (along with graph isomorphism problem). It seems there is quite some progress, so I hope to see it being resolved during my lifetime. In the meantime, we considered graph families for which reconstruction conjecture is known to be true and tried to come up with the easiest family of graphs that is still not resolved and have very few vertices. The resulted family is a type of bidegreed graphs (close to regular) on 20 vertices, which is probably possible to verify on the computer (though it would take a year or so).












CLIP based video search.
Работает на английском, русский можно докинуть, смысл в том что можно делать поиск по кадрам в видео.

https://colab.research.google.com/drive/1yFmmfx9T5ZW501UpfPRN-9kgAQ6F9GKM?usp=sharing

Показано 20 последних публикаций.

16

подписчиков
Статистика канала