TabFormer
pygod
TabFormer | pygod | |
---|---|---|
10 | 3 | |
297 | 1,217 | |
2.7% | 2.2% | |
0.0 | 8.6 | |
9 months ago | 16 days ago | |
Python | Python | |
Apache License 2.0 | BSD 2-clause "Simplified" License |
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.
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.
pygod
-
RAG Using Structured Data: Overview and Important Questions
Ok, using ChatGPT and Bard (the irony lol) I learned a bit more about GNNs:
GNNs are probabilistic and can be trained to learn representations in graph-structured data and handling complex relationships, while classical graph algorithms are specialized for specific graph analysis tasks and operate based on predefined rules/steps.
* Why is PyG it called "Geometric" and not "Topologic" ?
Properties like connectivity, neighborhoods, and even geodesic distances can all be considered topological features of a graph. These features remain unchanged under continuous deformations like stretching or bending, which is the defining characteristic of topological equivalence. In this sense, "PyTorch Topologic" might be a more accurate reflection of the library's focus on analyzing the intrinsic structure and connections within graphs.
However, the term "geometric" still has some merit in the context of PyG. While most GNN operations rely on topological principles, some do incorporate notions of Euclidean geometry, such as:
- Node embeddings: Many GNNs learn low-dimensional vectors for each node, which can be interpreted as points in a vector space, allowing geometric operations like distances and angles to be applied.
- Spectral GNNs: These models leverage the eigenvalues and eigenvectors of the graph Laplacian, which encodes information about the geometric structure and distances between nodes.
- Manifold learning: Certain types of graphs can be seen as low-dimensional representations of high-dimensional manifolds. Applying GNNs in this context involves learning geometric properties on the manifold itself.
Therefore, although topology plays a primary role in understanding and analyzing graphs, geometry can still be relevant in certain contexts and GNN operations.
* Real world applications:
- HuggingFace has a few models [0] around things like computational chemistry [1] or weather forecasting.
- PyGod [2] can be used for Outlier Detection (Anomaly Detection).
- Apparently ULTRA [3] can "infer" (in the knowledge graph sense), that Michael Jackson released some disco music :-p (see the paper).
- RGCN [4] can be used for knowledge graph link prediction (recovery of missing facts, i.e. subject-predicate-object triples) and entity classification (recovery of missing entity attributes).
- GreatX [5] tackles removing inherent noise, "Distribution Shift" and "Adversarial Attacks" (ex: noise purposely introduced to hide a node presence) from networks. Apparently this is a thing and the field is called "Graph Reliability" or "Reliable Deep Graph Learning". The author even has a bunch of "awesome" style lists of links! [6]
- Finally this repo has a nice explanation of how/why to run machine learning algorithms "outside of the DB":
"Pytorch Geometric (PyG) has a whole arsenal of neural network layers and techniques to approach machine learning on graphs (aka graph representation learning, graph machine learning, deep graph learning) and has been used in this repo [7] to learn link patterns, also known as link or edge predictions."
--
0: https://huggingface.co/models?pipeline_tag=graph-ml&sort=tre...
1: https://github.com/Microsoft/Graphormer
2: https://github.com/pygod-team/pygod
3: https://github.com/DeepGraphLearning/ULTRA
4: https://huggingface.co/riship-nv/RGCN
5: https://github.com/EdisonLeeeee/GreatX
6: https://edisonleeeee.github.io/projects.html
7: https://github.com/Orbifold/pyg-link-prediction
- GitHub - pygod-team/pygod: A Python Library for Graph Outlier Detection (Anomaly Detection)
- PyGOD: Library for graph outlier detection (anomaly detection)
What are some alternatives?
Transformers4Rec - Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.
pyod - A Comprehensive and Scalable Python Library for Outlier Detection (Anomaly Detection)