
Product
Introducing Socket MCP for Claude Desktop
Add secure dependency scanning to Claude Desktop with Socket MCP, a one-click extension that keeps your coding conversations safe from malicious packages.
Pytorch implementation of echo state networks for static graphs and discrete-time dynamic graphs.
Easiest way to get our library is via python package:
pip install graphesn
The library is quite straightforward to use:
from graphesn import StaticGraphReservoir, Readout, initializer
from torch_geometric.data import Data
data = Data(...)
reservoir = StaticGraphReservoir(num_layers=3, in_features=8, hidden_features=16)
reservoir.initialize_parameters(recurrent=initializer('uniform', rho=.9), input=initializer('uniform', scale=1))
embeddings = reservoir(data.edge_index, data.x)
readout = Readout(num_features=reservoir.out_features, num_targets=3)
readout.fit(data=(embeddings, data.y), regularization=1e-3)
predictions = readout(embeddings)
The library is contained in folder src/graphesn
:
reservoir.py
implementation of reservoirs for static and discrete-time dynamic graphs;matrix.py
random matrices generating functions;readout.py
implementation of a linear readout for large-scale ridge regression;data.py
classes to represent temporal and dynamic graphs;dataset.py
some dynamic graph datasets;util.py
general utilities.The examples
folder contains demos for our library on some common graph datasets.
This research software is provided as-is. We are working on this library in our spare time.
Code is released under the MIT license, see LICENSE
for details.
If you find a bug, please open an issue to report it, and we will do our best to solve it. For general or technical questions, please email us rather than opening an issue.
FAQs
Python implementation of Deep Graph Echo State Networks
We found that graphesn demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 3 open source maintainers collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Product
Add secure dependency scanning to Claude Desktop with Socket MCP, a one-click extension that keeps your coding conversations safe from malicious packages.
Product
Socket now supports Scala and Kotlin, bringing AI-powered threat detection to JVM projects with easy manifest generation and fast, accurate scans.
Application Security
/Security News
Socket CEO Feross Aboukhadijeh and a16z partner Joel de la Garza discuss vibe coding, AI-driven software development, and how the rise of LLMs, despite their risks, still points toward a more secure and innovative future.