Transformers4Rec
TabFormer
Our great sponsors
| Transformers4Rec | TabFormer | |
|---|---|---|
| 4 | 10 | |
| 1,030 | 295 | |
| 4.1% | 3.7% | |
| 5.3 | 0.0 | |
| 2 days ago | 9 months ago | |
| Python | Python | |
| Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Transformers4Rec
- New item prediction modules in open source libraries
-
Okay Do you think a recommendation engine for a final year project is too simple?
It's fine for a thesis project IMO! Recommendation is very much an active field with cool recent developments. If your supervisors are still sceptical you could try implementing one of the recent papers that apply transformers (like https://github.com/NVIDIA-Merlin/Transformers4Rec) or zone in on cold start problems in your domain.
- Show HN: Transformers4Rec -a new library for Transformers on Recommender Systems
TabFormer
-
Time-based splitting performing significantly worse than random splitting
Hi, I am currently working on a basic binary classifier for a transaction dataset, to predict which transaction is fraudulent (Dataset: https://github.com/IBM/TabFormer). The following is a quick summary of the dataset:
-
Question regarding Relational Graph Convolutional Network for a Fraud Detection problem
I am currently working on a transaction dataset (https://github.com/IBM/TabFormer/tree/main/data/credit_card) and I intend to build a fraud detection engine, but with tabular data transformed into a graph. I have used this article as my main outline for this approach: https://developer.nvidia.com/blog/optimizing-fraud-detection-in-financial-services-with-graph-neural-networks-and-nvidia-gpus/.
- TabFormer: NEW Data - star count:231.0
-
[D] Neural Networks are not the only universal approximators, so why are they so uniquely effective?
When people talk about tabular data they mean something with like <100 columns where your classification might strongly depend on a handful of specific ones. There is of course a regime where data is "somewhat" tabular (some NLP problems) so it's not entirely well-defined. And there are NN architecture for tabular data like the tabformer.
What are some alternatives?
NeuRec - Next RecSys Library
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
bertviz - BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
BERT-pytorch - Google AI 2018 BERT pytorch implementation
quickai - QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.
kogpt - KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)
zeroshot_topics - Topic Inference with Zeroshot models
Multimodal-Toolkit - Multimodal model for text and tabular data with HuggingFace transformers as building block for text data
pygod - A Python Library for Graph Outlier Detection (Anomaly Detection)
Neural-Scam-Artist - Web Scraping, Document Deduplication & GPT-2 Fine-tuning with a newly created scam dataset.
falcongpt - Simple GPT app that uses the falcon-7b-instruct model with a Flask front-end.