🏆 CIKM 2025 Best Full Paper Award! 🚀 We are thrilled to announce that we have won the prestigious Best Full Paper Award at CIKM 2025 for our work, "Reconsidering the Performance of GAE in Link Prediction"! 🎉 #CIKM2025 #GraphML #BestPaper

mulabpku's tweet image. 🏆 CIKM 2025 Best Full Paper Award! 🚀

We are thrilled to announce that we have won the prestigious Best Full Paper Award at CIKM 2025 for our work, "Reconsidering the Performance of GAE in Link Prediction"! 🎉

 #CIKM2025 #GraphML #BestPaper
mulabpku's tweet image. 🏆 CIKM 2025 Best Full Paper Award! 🚀

We are thrilled to announce that we have won the prestigious Best Full Paper Award at CIKM 2025 for our work, "Reconsidering the Performance of GAE in Link Prediction"! 🎉

 #CIKM2025 #GraphML #BestPaper

Always happy to chat about graphs, generative models, or spatial omics while in San Diego. 🌊 See you there! 1️⃣openreview.net/forum?id=d2Eou… 2️⃣openreview.net/forum?id=5ofJy… 3️⃣ arxiv.org/abs/2509.06743 #MachineLearning #GraphML #GenerativeModels #SpatialTranscriptomics


“DiffGR: A Discrete Diffusion‑Based Model for Personalised Recommendation by Reconstructing User‑Item Bipartite Graphs” Meet DiffGR here 👇 link.springer.com/chapter/10.100… #GraphML #Recommendation #DiffusionModels


Ecstatic✨ to share that I'm headed to @CarnegieMellon @mldcmu for a Ph.D. in Machine Learning this Fall! As I gear up to graduate from @IIITDelhi👨🏻‍🎓 with a #BTech in #csai, I'm exhilarated for this exciting new journey at @SCSatCMU. I'll be working on #GraphML & #NLProc!

karishgrover's tweet image. Ecstatic✨ to share that I'm headed to @CarnegieMellon @mldcmu for a Ph.D. in Machine Learning this Fall! As I gear up to graduate from @IIITDelhi👨🏻‍🎓 with a #BTech in #csai, I'm exhilarated for this exciting new journey at @SCSatCMU. I'll be working on #GraphML & #NLProc!

Finally leveraging the opportunity to attend events in Bay Area. Very excited! @Stanford #GraphML #workshop

DobkoMaria's tweet image. Finally leveraging the opportunity to attend events in Bay Area. Very excited! @Stanford #GraphML #workshop

The @LogConference, the leading conference dedicated to graph machine learning, is happening! Submission deadline: September 11th, 2024 Final decision: November 13th, 2024 Don't miss out on this opportunity! More details at logconference.org/cfp/#LoG2024 #GraphML #MachineLearning


My latest article: “Unleashing the Power of Data: Integrating Knowledge Graphs and Retrieval Augmented Generation with…” by Jason Kronemeyer #GraphDataScience #GraphML #Neo4j #JKnowledge medium.com/@jfkrone/unlea…

jasonkronemeyer's tweet image. My latest article: 
“Unleashing the Power of Data: Integrating Knowledge Graphs and Retrieval Augmented Generation with…” by Jason Kronemeyer #GraphDataScience #GraphML #Neo4j #JKnowledge medium.com/@jfkrone/unlea…

🚨 Exciting news! We released 🎱 tgp (Torch Geometric Pool), the library for pooling in Graph Neural Networks. 🚀 Get started with our tutorials: torch-geometric-pool.readthedocs.io/en/latest/tuto… With @IvanMarisca and Carlo Abate. #GraphML #GNN #Pooling #Pyg

FilippoMariaBi1's tweet image. 🚨 Exciting news! We released 🎱 tgp (Torch Geometric Pool), the library for pooling in Graph Neural Networks.

🚀 Get started with our tutorials: torch-geometric-pool.readthedocs.io/en/latest/tuto…

With @IvanMarisca and Carlo Abate.

#GraphML #GNN #Pooling #Pyg

Excited to share that I’ve joined @Meta as a Visiting Researcher for the next year, in their Pittsburgh office, alongside my PhD at @mldcmu. I’ll be working on #GeometricDL and #GraphML, with @YinglongXia & @zimplex4, under the @AIatMeta AI Mentorship Program.


📢 I am going on the job market for 2024! I've built pipelines with stats & ML methods (including #GraphML) applied to -omics datasets for biomarker discovery. I'm looking for industry & academia positions. Pls reach out if you're hiring or you've advice for the job search! 🤗


From Graph Benchmark Challenges to future #GNN breakthroughs, this #GraphML piece from @Mila_Quebec's @michael_galkin is a must-read for anyone working with Graph Neural Networks in 2023 ⬇️ hubs.la/Q01wRfd10

graphcoreai's tweet image. From Graph Benchmark Challenges to future #GNN breakthroughs, this #GraphML piece from @Mila_Quebec's @michael_galkin is a must-read for anyone working with Graph Neural Networks in 2023 ⬇️ 
hubs.la/Q01wRfd10

𝗚𝗿𝗮𝗽𝗵𝘀 + 𝗟𝗟𝗠𝘀: 𝗔 𝗡𝗮𝘁𝘂𝗿𝗮𝗹 𝗙𝗶𝘁? Glad to share our latest preprint: Graph Linearization Methods for Reasoning on Graphs with Large Language Models (now on arXiv: arxiv.org/abs/2410.19494) #LLMs #GraphML #NLP #AIResearch #MultimodalAI


The preprint of our work "DINE: Dimensional Interpretability of Node Embeddings", made with @meghakhosla, @apanisson and @run4avi is out on @arxiv! Great collaboration that started with a @SoBigData Transnational Access. arxiv.org/abs/2310.01162 #TNA #XAI #GraphML

simonepiaggesi's tweet image. The preprint of our work "DINE: Dimensional Interpretability of Node Embeddings", made with @meghakhosla, @apanisson and @run4avi is out on @arxiv! 
Great collaboration that started with a @SoBigData Transnational Access.
arxiv.org/abs/2310.01162

#TNA #XAI #GraphML

📢 Last CFP for GbRPR 2025! Join us in Caen 🇫🇷 (June 25–27, 2025) for the GBRPr, a workshop on Graphs and Pattern Recognition. ✨ Journal Specia Issue and proceedings ✨ Talks by C. Solnon & F. Malliaros ✨ Paper deadline: Feb 3 ✨ Low fees 🎉 iapr.org/gbr2025 #GraphML


Always happy to chat about graphs, generative models, or spatial omics while in San Diego. 🌊 See you there! 1️⃣openreview.net/forum?id=d2Eou… 2️⃣openreview.net/forum?id=5ofJy… 3️⃣ arxiv.org/abs/2509.06743 #MachineLearning #GraphML #GenerativeModels #SpatialTranscriptomics


🙏 A big thank you to the reviewers, thoughtful reviews, constructive points, & even disagreements. We truly appreciate the time, and efforts. 💻 🧵 📄 Code & Data, X thread, Preprint in thread. github.com/rethinking-gra… #GraphML #LanguageModels #MultimodalAI #GraphReasoning


“DiffGR: A Discrete Diffusion‑Based Model for Personalised Recommendation by Reconstructing User‑Item Bipartite Graphs” Meet DiffGR here 👇 link.springer.com/chapter/10.100… #GraphML #Recommendation #DiffusionModels


🏆 CIKM 2025 Best Full Paper Award! 🚀 We are thrilled to announce that we have won the prestigious Best Full Paper Award at CIKM 2025 for our work, "Reconsidering the Performance of GAE in Link Prediction"! 🎉 #CIKM2025 #GraphML #BestPaper

mulabpku's tweet image. 🏆 CIKM 2025 Best Full Paper Award! 🚀

We are thrilled to announce that we have won the prestigious Best Full Paper Award at CIKM 2025 for our work, "Reconsidering the Performance of GAE in Link Prediction"! 🎉

 #CIKM2025 #GraphML #BestPaper
mulabpku's tweet image. 🏆 CIKM 2025 Best Full Paper Award! 🚀

We are thrilled to announce that we have won the prestigious Best Full Paper Award at CIKM 2025 for our work, "Reconsidering the Performance of GAE in Link Prediction"! 🎉

 #CIKM2025 #GraphML #BestPaper

(7/7) More at 👇 📘 FedGraph: openreview.net/forum?id=d48Hj… 📘 FedLink: openreview.net/forum?id=D7PiC… 🌍 Federated Graph Learning — shaping the next frontier of privacy-aware, multi-agent AI. #NeurIPS2025 #GraphML #FederatedLearning #PrivacyAI #FedGraph #FedLink #AIResearch


🚀 New move spotted: @karishgrover joins Meta AI as a Visiting Researcher, while pursuing his PhD at CMU. His work? #GeometricDL & #GraphML 🌐 Check out his profile on @dinq_io ⬇️

dinq_me's tweet image. 🚀 New move spotted: @karishgrover joins Meta AI as a Visiting Researcher, while pursuing his PhD at CMU.
His work? #GeometricDL & #GraphML 🌐

Check out his profile on @dinq_io ⬇️

Excited to share that I’ve joined @Meta as a Visiting Researcher for the next year, in their Pittsburgh office, alongside my PhD at @mldcmu. I’ll be working on #GeometricDL and #GraphML, with @YinglongXia & @zimplex4, under the @AIatMeta AI Mentorship Program.



Excited to share that I’ve joined @Meta as a Visiting Researcher for the next year, in their Pittsburgh office, alongside my PhD at @mldcmu. I’ll be working on #GeometricDL and #GraphML, with @YinglongXia & @zimplex4, under the @AIatMeta AI Mentorship Program.


Have you checked out S-CGIB? github.com/NSLab-CUK/S-CG… Our molecular graph model, accepted at #AAAI25, showed #SOTA results on molecular property prediction. A gentle reminder to explore! 🚀 #GraphML #GNNs #SOTA


A quick reminder: Workshop on Graph-Augmented LLMs (GaLM) at @ICDM2025 is still accepting submissions! #LLM #GraphML #GraphAnalytics 📝 Papers — Extended deadline: September 5 More Info to submit your work here: iitbhu.ac.in/cf/jcsic/activ…

AMIT_GKP's tweet image. A quick reminder: Workshop on Graph-Augmented LLMs (GaLM) at @ICDM2025 is still accepting submissions! #LLM #GraphML #GraphAnalytics

📝 Papers — Extended deadline: September 5

More Info to submit your work here: iitbhu.ac.in/cf/jcsic/activ…
AMIT_GKP's tweet image. A quick reminder: Workshop on Graph-Augmented LLMs (GaLM) at @ICDM2025 is still accepting submissions! #LLM #GraphML #GraphAnalytics

📝 Papers — Extended deadline: September 5

More Info to submit your work here: iitbhu.ac.in/cf/jcsic/activ…

🧬 Thu 7 Aug | 5 PM EAT: Dr Michalis K. Titsias (DeepMind) on Learning-Order Autoregressive Models for Molecular Graph Gen 🚀 SOTA on QM9 & ZINC250k! 🔗 calendar.app.google/X2JaaTwLsaVSqV… 🌐 theciggroup.net #AI #GraphML #DeepMind #CIG

lukman_bukenya's tweet image. 🧬 Thu 7 Aug | 5 PM EAT: Dr Michalis K. Titsias (DeepMind) on Learning-Order Autoregressive Models for Molecular Graph Gen 🚀 SOTA on QM9 & ZINC250k!
🔗 calendar.app.google/X2JaaTwLsaVSqV…
🌐 theciggroup.net
#AI #GraphML #DeepMind #CIG

rijitK's tweet card. KDD 2025 - Finding Counterfactual Evidences for Node Classification

youtube.com

YouTube

KDD 2025 - Finding Counterfactual Evidences for Node Classification

Come to the paper & poster sessions of my PhD student @DazhuoQiu @kdd_news #KDD25 #KDD2025 for our paper "𝘍𝘪𝘯𝘥𝘪𝘯𝘨 𝘊𝘰𝘶𝘯𝘵𝘦𝘳𝘧𝘢𝘤𝘵𝘶𝘢𝘭 𝘌𝘷𝘪𝘥𝘦𝘯𝘤𝘦𝘴 𝘧𝘰𝘳 𝘕𝘰𝘥𝘦 𝘊𝘭𝘢𝘴𝘴𝘪𝘧𝘪𝘤𝘢𝘵𝘪𝘰𝘯" arxiv.org/pdf/2505.11396 (work w/ @FrancescoBonchi) 👇



What if message passing in GNNs followed hyperbolic PDEs? This work reformulates GNN dynamics as a hyperbolic PDE system, mapping node features into eigenvector solution spaces unlocking topological interpretability Boosts performance across graph tasks #GraphML #icml2025 #AI #ML


🚨 Reviewer Call — LoG 2025 📷 Passionate about graph ML or GNNs? Help shape the future of learning on graphs by reviewing for the LoG 2025 conference! 📷forms.gle/Ms21k7oE8kF1Pd… 📷 RT & share! #GraphML #GNN #ML #AI #CallForReviewers


Just read a cool paper at #ICML2025: ML2-GCL – a manifold learning inspired, lightweight GCL method that: 1. Avoids risky augmentations with single-view design 2. Recovers global structure from local fits 3. Offers a closed-form solution, boosting efficiency #GraphML #AI #ML #DL


🚨 Calling all ML & AI companies! The LOG 2025 sponsor page is now live: logconference.org/sponsors/ LOG is the go-to venue for graph ML, reasoning & systems research. We're inviting sponsors to support this fast-growing community & gain visibility. #LOG2025 #GraphML #MachineLearning


Excited to be in Vancouver this week for #ICML2025!🌍✈️. Presenting our paper on curvature-based graph anomaly detection: 📍 East Exhibition Hall A-B E2900 📅 Tue, 15 July | 4:30 – 7:00 PM PDT 🔗 arxiv.org/abs/2502.08605 Drop by to chat about #geometricDL and #graphML! 🚀🧩

New paper alert! 🚀📈 #ICML2025 @icmlconf Can graph curvature uncover hidden anomalies overlooked by traditional methods? 💡Introducing CurvGAD, a mixed-curvature graph autoencoder designed to detect curvature-based geometric anomalies. 🔗 arxiv.org/pdf/2502.08605 (1/9)

karishgrover's tweet image. New paper alert! 🚀📈 #ICML2025 @icmlconf

Can graph curvature uncover hidden anomalies overlooked by traditional methods? 

💡Introducing CurvGAD, a mixed-curvature graph autoencoder designed to detect curvature-based geometric anomalies.

🔗 arxiv.org/pdf/2502.08605

(1/9)


🏆 CIKM 2025 Best Full Paper Award! 🚀 We are thrilled to announce that we have won the prestigious Best Full Paper Award at CIKM 2025 for our work, "Reconsidering the Performance of GAE in Link Prediction"! 🎉 #CIKM2025 #GraphML #BestPaper

mulabpku's tweet image. 🏆 CIKM 2025 Best Full Paper Award! 🚀

We are thrilled to announce that we have won the prestigious Best Full Paper Award at CIKM 2025 for our work, "Reconsidering the Performance of GAE in Link Prediction"! 🎉

 #CIKM2025 #GraphML #BestPaper
mulabpku's tweet image. 🏆 CIKM 2025 Best Full Paper Award! 🚀

We are thrilled to announce that we have won the prestigious Best Full Paper Award at CIKM 2025 for our work, "Reconsidering the Performance of GAE in Link Prediction"! 🎉

 #CIKM2025 #GraphML #BestPaper

I just wrote a blog for all of you who want to step into this beautiful world of Graph ML but you're not sure how to start. Blog: gordicaleksa.medium.com/how-to-get-sta… I shared exciting applications. I shared and structured the resources. And much more. #graphml

gordic_aleksa's tweet image. I just wrote a blog for all of you who want to step into this beautiful world of Graph ML but you're not sure how to start.

Blog: gordicaleksa.medium.com/how-to-get-sta…

I shared exciting applications.

I shared and structured the resources.

And much more.

#graphml

New GNNs? On Tuesday in the #GraphML reading group James Rowbottom and @b_p_chamberlain present their "GRAND: Graph Neural Diffusion" + their #NeurIPS2021 paper "Beltrami Flow and Neural Diffusion on Graphs" out of @mmbronstein's group @Twitter! Zoom: hannes-stark.com/logag-reading-… 1/2

HannesStaerk's tweet image. New GNNs? On Tuesday in the #GraphML reading group James Rowbottom and @b_p_chamberlain present their "GRAND: Graph Neural Diffusion" + their #NeurIPS2021 paper "Beltrami Flow and Neural Diffusion on Graphs" out of @mmbronstein's group @Twitter!

Zoom: hannes-stark.com/logag-reading-…
1/2

Day 71-76 of #100DaysOfCode For a graph-level classification task: ✅Trained a GCN-based model ✅Trained a Chebnet-based model #GraphML #geometricDL #WomenInSTEM #WomenWhoCode

elisagdelope's tweet image. Day 71-76 of #100DaysOfCode

For a graph-level classification task:
✅Trained a GCN-based model 
✅Trained a Chebnet-based model

#GraphML #geometricDL 
#WomenInSTEM #WomenWhoCode

KeyError exception while reading a GraphML file with NetworkX occurs in Visual Studio 2017 but not Spyder stackoverflow.com/questions/6537… #visualstudio2017 #python #graphml #networkx

overflow_meme's tweet image. KeyError exception while reading a GraphML file with NetworkX occurs in Visual Studio 2017 but not Spyder stackoverflow.com/questions/6537… #visualstudio2017 #python #graphml #networkx

🚀 Unlock the future of data science with our comprehensive suite featuring Graph Analytics, GraphML, and Graph-Powered GenAI, powered by the ArangoDB LangChain Integration Pack! Register Now:- okt.to/Sm5g7P #DataScience #GraphML #GraphRAG #LangChain

arangoai's tweet image. 🚀 Unlock the future of data science with our comprehensive suite featuring Graph Analytics, GraphML, and Graph-Powered GenAI, powered by the ArangoDB LangChain Integration Pack! 

Register Now:- okt.to/Sm5g7P

#DataScience #GraphML #GraphRAG #LangChain

Day 12 of #100DaysOfCode Revisited spectral clustering lecture. Oh, the magic of eigendecomposition 🧙‍♀️✨ #GraphML #AI #WomenWhoCode #WomenInSTEM


Days 68 & 69 of #100Daysofcode ✅ Created my own dataset from PyG's InMemoryDataset class (see below MyOmicsDataset) ➡️ Stored 578 graphs on it ➡️ Each graph having nodes features & graph label #GraphML #WomenWhoCode #WomenInSTEM

elisagdelope's tweet image. Days 68 & 69 of #100Daysofcode 

✅ Created my own dataset from PyG's InMemoryDataset class (see below MyOmicsDataset)
➡️ Stored 578 graphs on it
➡️ Each graph having nodes features & graph label

#GraphML #WomenWhoCode #WomenInSTEM

New year is a good time to is a good time to recap and make predictions. In a new post in @TDataScience I sought the opinion of 12 prominent researchers in the field of #GraphML to predict what is in store for 2021. towardsdatascience.com/predictions-an…

mmbronstein's tweet image. New year is a good time to is a good time to recap and make predictions. In a new post in @TDataScience I sought the opinion of 12 prominent researchers in the field of #GraphML to predict what is in store for 2021. 

towardsdatascience.com/predictions-an…

Days 5 & 6 of #100DaysOfCode ✅ Finished Homework 1 of the #CS224W course ✅ Uploaded to github Next week I'll deepen into feature-based methods and community detection algorithms. #GraphML #AI #WomenWhoCode #womenintech

elisagdelope's tweet image. Days 5 & 6 of #100DaysOfCode 

✅ Finished Homework 1 of the #CS224W course 
✅ Uploaded to github

Next week I'll deepen into feature-based methods and community detection algorithms. 

#GraphML #AI #WomenWhoCode #womenintech

Ecstatic✨ to share that I'm headed to @CarnegieMellon @mldcmu for a Ph.D. in Machine Learning this Fall! As I gear up to graduate from @IIITDelhi👨🏻‍🎓 with a #BTech in #csai, I'm exhilarated for this exciting new journey at @SCSatCMU. I'll be working on #GraphML & #NLProc!

karishgrover's tweet image. Ecstatic✨ to share that I'm headed to @CarnegieMellon @mldcmu for a Ph.D. in Machine Learning this Fall! As I gear up to graduate from @IIITDelhi👨🏻‍🎓 with a #BTech in #csai, I'm exhilarated for this exciting new journey at @SCSatCMU. I'll be working on #GraphML & #NLProc!

How to create Heterogeneous GNNs using PyTorchGeometric. ⭐️ Using to_hetero(): Convert a homogeneous GNN model to a heterogeneous GNN. ⭐️ Using HeteroConv: This allows you to define custom heterogeneous message-passing functions for different edge types. #gnn #nn #graphml #pyg

hellorahulk's tweet image. How to create Heterogeneous GNNs using PyTorchGeometric.

⭐️ Using to_hetero(): Convert a homogeneous GNN model to a heterogeneous GNN.

⭐️ Using HeteroConv: This allows you to define custom heterogeneous message-passing functions for different edge types.

#gnn #nn #graphml #pyg

Day 23 & 24 #100DaysOfCode Holidays are over and I've been working on classical #GNN layers: how they r defined, which components they include. Some architectrs: GCN, GraphSAGE & GAT. Combine different aspects of design ➡️ performance🆙 #GraphML #AI #WomenWhoCode #womenintech

elisagdelope's tweet image. Day 23 & 24 #100DaysOfCode

Holidays are over and I've been working on classical #GNN layers: how they r defined, which components they include.

Some architectrs: GCN, GraphSAGE & GAT.

Combine different aspects of design ➡️ performance🆙

#GraphML #AI #WomenWhoCode #womenintech

Day 9 of #100daysofcodechallenge Today I learned the notion of encoders/decoders applied to nodes in a graph. Deepwalk and node2vec methods coming in the next day(s). #GraphML #AI #WomenWhoCode #WomenInSTEM #100DaysOfCode


Day 10 of #100DaysOfCode Today I covered random walk approaches for node embeddings: deepwalk & node2vec. The conclusion of this lecture and last one(s) is... 👇 #GraphML #WomenWhoCode #AI

elisagdelope's tweet image. Day 10 of #100DaysOfCode 

Today I covered random walk approaches for node embeddings: deepwalk & node2vec. 

The conclusion of this lecture and last one(s) is... 👇

#GraphML #WomenWhoCode #AI

Day 31 of #100DaysOfCode Inference with Belief propagation on Conditional Random Field (a special case of Markov Random Fields to model conditional prob. distribution) I was a bit rusty on cond. probs but I went thru in the end!🙌 #GraphML #AI #WomenWhoCode #womenintech

elisagdelope's tweet image. Day 31 of #100DaysOfCode 

Inference with Belief propagation on Conditional Random Field (a special case of Markov Random Fields to model conditional prob. distribution)

I was a bit rusty on cond. probs but I went thru in the end!🙌

#GraphML #AI #WomenWhoCode #womenintech

Finally leveraging the opportunity to attend events in Bay Area. Very excited! @Stanford #GraphML #workshop

DobkoMaria's tweet image. Finally leveraging the opportunity to attend events in Bay Area. Very excited! @Stanford #GraphML #workshop

Day 60 of #100DaysOfCode I've been playing with Cora dataset: Node degree distribution, found the most connected nodes in the network, explored the classes and the notion of homophily. And then the best part 👇 #GraphML #WomenWhoCode #WomenInSTEM

elisagdelope's tweet image. Day 60 of #100DaysOfCode 

I've been playing with Cora dataset: Node degree distribution, found the most connected nodes in the network, explored the classes and the notion of homophily. 

And then the best part 👇

#GraphML #WomenWhoCode #WomenInSTEM

After a hectic month off the #100DaysOfCode challenge, I'm back. Day 52!💥🦾 👉Working on @m_deff 's GCNN implementation for a signal classification task in #Keras ✅Loaded + numpyed features, adj matrix & labels 🚧Coarsening the graph #GraphML #AI #WomenWhoCode #WomenInSTEM

elisagdelope's tweet image. After a hectic month off the #100DaysOfCode challenge, I'm back. Day 52!💥🦾

👉Working on @m_deff 's GCNN implementation for a signal classification task in #Keras

✅Loaded + numpyed features, adj matrix & labels
🚧Coarsening the graph

#GraphML #AI #WomenWhoCode #WomenInSTEM

Loading...

Something went wrong.


Something went wrong.


United States Trends