Hamed Shirzad
@hamedshirzad.bsky.social
PhD student in Computer Science at UBC | Exploring Machine Learning on Graphs
https://www.hamedshirzad.com/
https://www.hamedshirzad.com/
Pinned
Graph Transformers (GTs) can handle long-range dependencies and resolve information bottlenecks, but they’re computationally expensive. Our new model, Spexphormer, helps scale them to much larger graphs – check it out at NeurIPS next week, or the preview here!
[1/13]
#NeurIPS2024
[1/13]
#NeurIPS2024
Enjoyed giving our tutorial on Geometric & Topological Deep Learning at IEEE MLSP 2025 alongside @semihcanturk.bsky.social. Loving the Istanbul vibes and the amazing food here! ✅
August 31, 2025 at 9:02 PM
Enjoyed giving our tutorial on Geometric & Topological Deep Learning at IEEE MLSP 2025 alongside @semihcanturk.bsky.social. Loving the Istanbul vibes and the amazing food here! ✅
Reposted by Hamed Shirzad
1/ Introducing TxPert: a new model that predicts transcriptional responses across diverse biological contexts
It’s designed to generalize across unseen single-gene perturbations, novel combinations of gene perturbations, and even new cell types 🧵
www.valencelabs.com/txpert-predi...
It’s designed to generalize across unseen single-gene perturbations, novel combinations of gene perturbations, and even new cell types 🧵
www.valencelabs.com/txpert-predi...
TxPert: Predicting Cellular Responses to Unseen Genetic Perturbations - Valence Labs
We introduce TxPert: a state-of-the-art model that leverages multiple biological knowledge networks to accurately predict transcriptional responses under OOD scenarios.
www.valencelabs.com
May 22, 2025 at 1:52 PM
1/ Introducing TxPert: a new model that predicts transcriptional responses across diverse biological contexts
It’s designed to generalize across unseen single-gene perturbations, novel combinations of gene perturbations, and even new cell types 🧵
www.valencelabs.com/txpert-predi...
It’s designed to generalize across unseen single-gene perturbations, novel combinations of gene perturbations, and even new cell types 🧵
www.valencelabs.com/txpert-predi...
Reposted by Hamed Shirzad
1/ At Valence Labs, @recursionpharma.bsky.social's AI research engine, we’re focused on advancing drug discovery outcomes through cutting-edge computational methods
Today, we're excited to share our vision for building virtual cells, guided by the predict-explain-discover framework 🧵
Today, we're excited to share our vision for building virtual cells, guided by the predict-explain-discover framework 🧵
May 20, 2025 at 3:55 PM
1/ At Valence Labs, @recursionpharma.bsky.social's AI research engine, we’re focused on advancing drug discovery outcomes through cutting-edge computational methods
Today, we're excited to share our vision for building virtual cells, guided by the predict-explain-discover framework 🧵
Today, we're excited to share our vision for building virtual cells, guided by the predict-explain-discover framework 🧵
Loved working on the TxPert project! It's also exciting to see my PhD work on Graph Transformers (Exphormer model) finding such meaningful application in a critical real-world task.
5/ As an important first step toward the Predict capability of this framework, we are also introducing TxPert: a state-of-the-art model for predicting transcriptional responses to genetic perturbations, especially in out-of-distribution scenarios
May 20, 2025 at 11:39 PM
Loved working on the TxPert project! It's also exciting to see my PhD work on Graph Transformers (Exphormer model) finding such meaningful application in a critical real-world task.
Huge congrats to my labmate @joshuaren.bsky.social and my supervisor @djsutherland.ml for receiving an Outstanding Paper Award at @iclr-conf.bsky.social for their work: "Learning Dynamics of LLM Finetuning" 🏆
So proud to see their amazing research recognized! 👏🔥
blog.iclr.cc/2025/04/22/a...
So proud to see their amazing research recognized! 👏🔥
blog.iclr.cc/2025/04/22/a...
Announcing the Outstanding Paper Awards at ICLR 2025 – ICLR Blog
blog.iclr.cc
April 23, 2025 at 12:04 PM
Huge congrats to my labmate @joshuaren.bsky.social and my supervisor @djsutherland.ml for receiving an Outstanding Paper Award at @iclr-conf.bsky.social for their work: "Learning Dynamics of LLM Finetuning" 🏆
So proud to see their amazing research recognized! 👏🔥
blog.iclr.cc/2025/04/22/a...
So proud to see their amazing research recognized! 👏🔥
blog.iclr.cc/2025/04/22/a...
As a reminder, we will have our poster session tomorrow:
📍 East Exhibit Hall, Poster #3010
📄 arxiv.org/abs/2411.16278
💻 github.com/hamed1375/Sp...
To motivate you further, we have some insights gained from the attention score analysis of this work, which I'll share in this thread:
📍 East Exhibit Hall, Poster #3010
📄 arxiv.org/abs/2411.16278
💻 github.com/hamed1375/Sp...
To motivate you further, we have some insights gained from the attention score analysis of this work, which I'll share in this thread:
Graph Transformers (GTs) can handle long-range dependencies and resolve information bottlenecks, but they’re computationally expensive. Our new model, Spexphormer, helps scale them to much larger graphs – check it out at NeurIPS next week, or the preview here!
[1/13]
#NeurIPS2024
[1/13]
#NeurIPS2024
December 12, 2024 at 12:29 AM
As a reminder, we will have our poster session tomorrow:
📍 East Exhibit Hall, Poster #3010
📄 arxiv.org/abs/2411.16278
💻 github.com/hamed1375/Sp...
To motivate you further, we have some insights gained from the attention score analysis of this work, which I'll share in this thread:
📍 East Exhibit Hall, Poster #3010
📄 arxiv.org/abs/2411.16278
💻 github.com/hamed1375/Sp...
To motivate you further, we have some insights gained from the attention score analysis of this work, which I'll share in this thread:
Reposted by Hamed Shirzad
After two years, our paper on generative models for structure-based drug design is finally out in @natcomputsci.bsky.social
www.nature.com/articles/s43...
www.nature.com/articles/s43...
Structure-based drug design with equivariant diffusion models - Nature Computational Science
This work applies diffusion models to conditional molecule generation and shows how they can be used to tackle various structure-based drug design problems
www.nature.com
December 9, 2024 at 2:00 PM
After two years, our paper on generative models for structure-based drug design is finally out in @natcomputsci.bsky.social
www.nature.com/articles/s43...
www.nature.com/articles/s43...
Graph Transformers (GTs) can handle long-range dependencies and resolve information bottlenecks, but they’re computationally expensive. Our new model, Spexphormer, helps scale them to much larger graphs – check it out at NeurIPS next week, or the preview here!
[1/13]
#NeurIPS2024
[1/13]
#NeurIPS2024
December 5, 2024 at 7:58 PM
Graph Transformers (GTs) can handle long-range dependencies and resolve information bottlenecks, but they’re computationally expensive. Our new model, Spexphormer, helps scale them to much larger graphs – check it out at NeurIPS next week, or the preview here!
[1/13]
#NeurIPS2024
[1/13]
#NeurIPS2024
Reposted by Hamed Shirzad
✨ Top Reviewers of LoG 2024 ✨
Thank you to our incredible reviewers who went above and beyond to provide thoughtful and constructive feedback! 🙏
👏 Your efforts are the backbone of LoG’s success!
Thank you to our incredible reviewers who went above and beyond to provide thoughtful and constructive feedback! 🙏
👏 Your efforts are the backbone of LoG’s success!
November 29, 2024 at 8:59 PM
✨ Top Reviewers of LoG 2024 ✨
Thank you to our incredible reviewers who went above and beyond to provide thoughtful and constructive feedback! 🙏
👏 Your efforts are the backbone of LoG’s success!
Thank you to our incredible reviewers who went above and beyond to provide thoughtful and constructive feedback! 🙏
👏 Your efforts are the backbone of LoG’s success!
Had a great time attending the @logconference.bsky.social meetup in Vancouver! Big thanks to the organizers, Renjie Liao and Oliver Schulte!
November 28, 2024 at 6:22 PM
Had a great time attending the @logconference.bsky.social meetup in Vancouver! Big thanks to the organizers, Renjie Liao and Oliver Schulte!
Reposted by Hamed Shirzad
NeurIPS Conference is now Live on Bluesky!
-NeurIPS2024 Communication Chairs
-NeurIPS2024 Communication Chairs
November 22, 2024 at 1:33 AM
NeurIPS Conference is now Live on Bluesky!
-NeurIPS2024 Communication Chairs
-NeurIPS2024 Communication Chairs
Our new preprint is out! 🚀
I’ll be presenting this work at the Machine Learning and Compression Workshop @ NeurIPS 2024. The research is still ongoing, and we’re working on deeper theoretical results. Stay tuned for a thread on our findings so far—coming soon!
arxiv.org/abs/2411.13028
I’ll be presenting this work at the Machine Learning and Compression Workshop @ NeurIPS 2024. The research is still ongoing, and we’re working on deeper theoretical results. Stay tuned for a thread on our findings so far—coming soon!
arxiv.org/abs/2411.13028
A Theory for Compressibility of Graph Transformers for Transductive Learning
Transductive tasks on graphs differ fundamentally from typical supervised machine learning tasks, as the independent and identically distributed (i.i.d.) assumption does not hold among samples. Instea...
arxiv.org
November 21, 2024 at 6:19 PM
Our new preprint is out! 🚀
I’ll be presenting this work at the Machine Learning and Compression Workshop @ NeurIPS 2024. The research is still ongoing, and we’re working on deeper theoretical results. Stay tuned for a thread on our findings so far—coming soon!
arxiv.org/abs/2411.13028
I’ll be presenting this work at the Machine Learning and Compression Workshop @ NeurIPS 2024. The research is still ongoing, and we’re working on deeper theoretical results. Stay tuned for a thread on our findings so far—coming soon!
arxiv.org/abs/2411.13028
Reposted by Hamed Shirzad
Two BioML starter packs now:
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)
Anybody have a bioml starter pack?
November 18, 2024 at 5:09 PM
Two BioML starter packs now:
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)
Reposted by Hamed Shirzad
Periodic reminder: submitting on #arXiv is great! But the source is available: good per se, but remember to remove LaTeX comments you don't want to be made public.
Thankfully, there are tools that do that (and more) easily and automatically for you! E.g., arXiv-collector:
github.com/djsutherland...
Thankfully, there are tools that do that (and more) easily and automatically for you! E.g., arXiv-collector:
github.com/djsutherland...
GitHub - djsutherland/arxiv-collector: A little Python script to collect LaTeX sources for upload to the arXiv.
A little Python script to collect LaTeX sources for upload to the arXiv. - djsutherland/arxiv-collector
github.com
November 18, 2024 at 2:35 AM
Periodic reminder: submitting on #arXiv is great! But the source is available: good per se, but remember to remove LaTeX comments you don't want to be made public.
Thankfully, there are tools that do that (and more) easily and automatically for you! E.g., arXiv-collector:
github.com/djsutherland...
Thankfully, there are tools that do that (and more) easily and automatically for you! E.g., arXiv-collector:
github.com/djsutherland...
Reposted by Hamed Shirzad
Hello World!
November 16, 2024 at 7:52 PM
Hello World!
Bluesky feels just like the good old days of Twitter!
November 16, 2024 at 7:09 PM
Bluesky feels just like the good old days of Twitter!
Reposted by Hamed Shirzad
Here is an initial starter pack list on Machine Learning on Graphs: go.bsky.app/HN2MTzp
Machine Learning on Graphs
Join the conversation
go.bsky.app
November 16, 2024 at 1:09 AM
Here is an initial starter pack list on Machine Learning on Graphs: go.bsky.app/HN2MTzp