#GraphML
LightNews LightNews
guillaumesalhagalvan.com
Some research update!

Happy to share that our #GraphML paper:

"To Share or Not to Share: Investigating Weight Sharing in Variational Graph Autoencoders"
co-authored with Jiaying Xu,

has been accepted for presentation at the ACM Web Conference #WWW2025! 🥳

Paper online soon. See you in Sydney!
2025 ACM Web Conference
January 21, 2025 at 8:28 AM
guillaumesalhagalvan.com
I’m in Sydney this week! 🇦🇺 Excited to attend #WWW2025, the 2025 ACM Web Conference.

Tomorrow, I’ll be presenting our paper, “To Share or Not to Share: Investigating Weight Sharing in Variational Graph Autoencoders,”
co-authored with Jiaying Xu.

#WebConf2025 #GraphML
April 30, 2025 at 6:51 AM
mingxunwang.bsky.social
LOL - fun problem to have. I think this might be possible - I think the main graphml, we'll just need to get the actual task and display title.
May 28, 2025 at 3:35 AM
logml.bsky.social
📣 LOGML'26 Speaker Series

🎤 Soledad Villar @soledadvillar.bsky.social (Johns Hopkins)

Her research spans equivariant ML, GNNs, with applications to computational biology.

📍 Imperial College London
📅 13–17 July 2026
🔗 www.logml.ai

#LOGML #GraphML #GeometricDeepLearning #SummerSchool
May 20, 2026 at 4:00 AM
itr.bsky.social
I use NetworkX to generate the core graph data and save it as a .gexf file. Then I load it up in Gephi to generate to use their layout and coloring algorithms, and save that as a .graphml file. And lastly I load that using NetworkX and draw it using a mix of Pillow and MatPlotLib for the left image.
November 17, 2024 at 10:32 AM
leuc.github.io
Explore 1.6 million diplomatic cables in 3D

The "Central Foreign Policy File" reference graph is available for download as GraphML
archive.org/details/cfpf...

Load GraphML into igraph-vlk - 3D graph exploration for the desktop
github.com/leuc/igraph-...

Open Source Code & Public Domain Data 🗃️ 📊
September 5, 2026 at 11:55 PM
amitkumarjaiswal.bsky.social
A quick reminder: Workshop on Graph-Augmented LLMs (GaLM): Bridging Language and Structured Knowledge is still accepting submissions at #IEEE #ICDM.

📝 Papers — Extended deadline: September 5

For more info and how to submit your work: iitbhu.ac.in/cf/jcsic/act...

#LLM #ML #AI #GraphML #RAG
August 30, 2025 at 12:59 PM
ikiga1.bsky.social
🎉 Our paper “The Generalized Skew Spectrum of Graphs” was accepted to ICML 2025!

We applied deep math - group theory, rep theory & Fourier analysis - to graph ML (no quantum this time!😄)

📍 See you in Vancouver in July!
📄 arxiv.org/abs/2505.23609

#ICML2025 #GraphML #AI #ML
The Generalized Skew Spectrum of Graphs
This paper proposes a family of permutation-invariant graph embeddings, generalizing the Skew Spectrum of graphs of Kondor & Borgwardt (2008). Grounded in group theory and harmonic analysis, our metho...
arxiv.org
May 30, 2025 at 12:07 PM
sluagh.bsky.social
Man. Immer, wenn man was interessantes macht, fliegt die Zeit. Schreibe gerade ein AWK script, um aus DDLs CSV-Dateien zu machen, mit denen man ein graphml Modell mit Gruppen und Joins erstellen kann. Quasi Datenbank-Dokumentation.
September 25, 2024 at 5:32 PM
thijs.niks.nu
Deleting a station also should remove any routes, so that is supposed to prevent this problem.

You can export and import graphml files (which are also text) but not csv
August 13, 2025 at 1:37 PM
davidciani.com
Why do people have non-printable control characters in their #bsky description fields? Trying to find the needle in the haystack thats preventing me from writing the GraphML xml file.

#atproto
November 6, 2025 at 7:36 PM
thijs.niks.nu
Love to hear that! Thank you for trying it.

The tool doesn’t sync projects, but you can export the graphml file on the iPad and import it on desktop if you want to transfer it
August 11, 2025 at 6:32 PM
tempgraphrg.bsky.social
Hi!
This thursday, nov 21st, 11am EST, Rishabh Ranjan will present:
RELBENCH: A Benchmark for Deep Learning on Relational Databases (NeurIPS 2024 Datasets and Benchmarks Track)
🎈
Join on zoom (link on website)

arxiv.org/pdf/2407.20060

#graphml #machinelearning #temporalgraphs #neurips
Position: Relational Deep Learning - Graph Representation Learning on Relational Databases
Much of the world’s most valued data is stored in relational databases and data warehouses, where the data is organized into tables connected by primary-foreign key relations. However, building mac...
proceedings.mlr.press
November 18, 2024 at 3:35 PM
logml.bsky.social
📣 LOGML 2026 Speaker Series

🎤 Dorina Thanou (EPFL)
Works on graph signal processing and ML, focusing on interpretable, robust models for biomedicine and AI for health.

🔗 Apply: forms.gle/RjxJHCdKVJF4...
🔗 Explore speakers: www.logml.ai/speakers/

⏳ Deadline: 10 May 2026

#LOGML #Geometry #GraphML
May 4, 2026 at 11:05 AM
salvatorecalderaro.bsky.social
www.linkedin.com/posts/salvat...
#graphneuralnetworks #bioinformatics #debruijngraphs #transcriptionfactors #deeplearning #proteinclassification #graphml #deeplearning #artificialintelligence | Salvatore Calderaro
🚀 Excited to introduce DeBruijnTFactor — a graph-based deep learning tool capable of predicting whether a protein contains transcription factors or not! DeBruijnTFactor models protein sequences as De...
www.linkedin.com
August 2, 2026 at 7:41 AM
logml.bsky.social
LOGML 2026 mentor applications are still open!
Deadline extended to 22 March 2026(AoE).

Mentor a small team at Imperial College London during 13–17 July'26.

Travel/accommodation support available.

🔗 logml.ai/apply.html

#LOGML #GeometricDeepLearning #GraphML #MachineLearning
LOGML 2026
London Geometry and Machine Learning Summer School, July 13-17 2026
logml.ai
March 17, 2026 at 9:39 AM
grant-h.mastodon.social.ap.brid.gy
A #higraph milestone: Blobs (nodes as sets) now work! Grab a 'parent' blob, and all the children move. Edges connect anywhere on the blob, and default to be orthogonal to the point of contact. graphML read and write working.

Now on to proper hyperedges!

#python #pyside6 #qt #graphtheory
A computer drawn higraph. A number of rectangular sets are connected by smoothly curving edges.
March 8, 2026 at 6:50 PM
rasterinterrupt.oldbytes.space.ap.brid.gy
#adventofcode Day 24: Crossed Wires

Oh boy. I did part 2 by hand. Exported the graph as a GraphML file, and imported it into Cytoscape. Arranging the gates was quite some work. Then it was obvious which gate outputs needed to be switched. Still, it took me […]

[Original post on oldbytes.space]
The graph is rendered in Cytoscape, with the incorrect gates marked in a different color.
December 25, 2024 at 4:41 AM
grant-h.mastodon.social.ap.brid.gy
#higraph progress!

Still got lots to do, but hyperEdges can now be saved & loaded in modified #GraphML files. The "model tree" on the left highlights items in the graph on the right.
I can see "minimum viable product"!

The #hyperedge structure is both […]

[Original post on mastodon.social]
A computer screen, with a classical menu & taskbar. The left panel contains hierarchical text. The right panel contains node, rounded-rectangle sets and multi-ended arrowed lines.
May 5, 2026 at 6:41 PM
panisson.bsky.social
Check out our poster at #LoG2024, based on our #TMLR paper:
📍 “A True-to-the-Model Axiomatic Benchmark for Graph-based Explainers”
🗓️ Tuesday 4–6 PM CET
📌 Poster Session 2, GatherTown
Join us to discuss graph ML explainability and benchmarks
#ExplainableAI #GraphML
openreview.net/forum?id=HSQTv3R8Iz
A poster with a light blue background, featuring the paper with title: “A True-to-the-Model Axiomatic Benchmark for Graph-based Explainers”. Authors: Corrado Monti, Paolo Bajardi, Francesco Bonchi, André Panisson, Alan Perotti Background Explainability in GNNs is crucial for enhancing trust understanding in machine learning models. Current benchmarks focus on data, ignoring the model’s actual decision logic, leading to gaps in understanding. Furthermore, existing methods often lack standardized benchmarks to measure their reliability and effectiveness. Motivation Reliable, standardised benchmarks are needed to ensure explainers reflect the internal logic of graph-based models, aiding in fairness, accountability, and regulatory compliance. Research Question If a model M is using a protected feature f , for instance using the gender of a user to classify whether their ads should gain more visibility, is a given explainer E able to detect it? Core Idea An explainer should detect if a model relies on specific features for node classification. Implements a “true-to-the-model” rather than “truth-to-the-data” logic. Key Components White-Box Classifiers: Local, Neighborhood, and Two-Hop Models with hardcoded logic for feature importance. Axioms: an explainer must assign higher scores to truly important features. Findings: Explainer Performance Deconvolution: Perfect fidelity but limited to GNNs. GraphLIME: Fails with non-local correlations and high sparsity. LRP/Integrated Gradients: Struggle with zero-valued features. GNNExplainer: Sensitive to sparsity and edge masking. Real-World Insights: Facebook Dataset Fidelity in detecting protected feature use in classification. Results for different explainers, highlighting strengths and limitations. Contributions: Proposed a rigorous framework for benchmarking explainers Demonstrated practical biases and flaws in popular explainers
November 26, 2024 at 5:27 PM
seanmhoban.bsky.social
Error installing a #rstats package? Try installing it from @github https://stackoverflow.com/questions/45318188/getting-error-in-function-igraph-write-graph-graphml-while-installing-igrap/45362040#comment77805669_45362040
May 23, 2025 at 11:32 AM
miriamposner.com
Is there a way to just view a gexf or graphML network online, since Retina seems to...not work?
January 21, 2025 at 7:31 PM
getnews-me.bsky.social
City‑Networks offers over 100 k road‑intersection nodes, pushing models to capture long‑range graph info, and adds a metric using output Jacobians of distant neighbors. Read more: https://getnews.me/large-scale-graph-dataset-measures-long-range-interactions/ #citynetworks #graphml #longrange
Large-Scale Graph Dataset Measures Long-Range Interactions
October 6, 2025 at 1:20 PM
getnews-me.bsky.social
Graph‑machine‑learning with Graph Autoencoders can detect hidden transaction patterns, and early results say it outperforms rule‑based fraud detection. Read more: https://getnews.me/graph-machine-learning-boosts-detection-of-financial-crime-patterns/ #graphml #frauddetection #fintech
Graph Machine Learning Boosts Detection of Financial Crime Patterns
September 18, 2025 at 10:39 AM
tomsawyersoftware.bsky.social
Want to simplify your data analysis? Dr. Ashleigh Faith breaks down how Tom Sawyer Software's suite empowers you to use graphML effortlessly. No coding? No problem! Watch her insightful review and unlock your data's potential: www.youtube.com/watch?v=1-AZ... #GraphML #TechReview
Knowledge Graph Technology Showcase for Tom Sawyer Software.
March 28, 2025 at 12:02 AM