imgremlin

ML RecSys @ Coinbase

[imgremlin @AlexTsepa]

@BoWang87 @UofT @Stanford Congratulations! Very very well deserved!

[imgremlin @AlexTsepa]

In our last work, we strived to replace the attention mechanism on graphs with a more efficient and powerful approach. And it... worked!

Hope to see follow-up works on the edge of sequential modeling and graph learning!

[Bo Wang @BoWang87]

State Spaces models (SSM) such as mamba have started to revolutionize languages, vision, and genomics, as a promising alternative to transformer architecture. How about graph data?

❤️‍🔥 Introducing Graph-Mamba, our latest innovation in Graph Learning for enhanced long-range graph context modeling!

🐍 Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces

AriXv: https://t.co/aNqA8vx1es
Code: https://t.co/qDKuaHM1R4

TL,DR 👇:
Graph Attention mechanisms face challenges in scaling for large graphs. Enter Graph-Mamba – integrating state space models with input-dependent node selection for efficient long-range context reasoning. Featuring special graph-centric adaptations to effectively employ SSM for non-sequential graph data.

🔑Key Contributions:
--Innovative Design: Graph-Mamba pioneers a novel graph network integrating selective SSM, capturing long-range dependencies with adaptive node selection.
--Adaptation for Graphs: Employing elegant node prioritization strategies and permutation-based training to mitigate sequence-induced biases and boost modeling power.
--Performance & Efficiency: Graph-Mamba outperforms baselines with linear-time complexity and up to 74% reduction in GPU memory consumption on large graphs.

❤️‍🔥 Looking Ahead: Propelling SSMs into an era of efficient pre-training on graph data with Graph-Mamba!
#GraphMamba #SSM #GraphTransformers #AIResearch #DataScience

Shoutout to Chloe Wang (@ChloeXWang1 ) for her leadership in this project and also to Oleksii Tsepa(@AlexTsepa ) and Jun Ma (@JunMa_11 ) for their invaluable contributions!

@UHNAIHUB @pmcc_ai @UHN @VectorInst @UofTCompSci @UofT_LMP

[imgremlin @AlexTsepa]

Poster session was awesome! What a great end to a Master's degree! #NeurIPS2023 #GNNs #DrugDiscovery

[Bo Wang @BoWang87]

Heading to #NeurIPS23 with two papers presented by my students and me:

1. BLEEP, a pioneering transformer-based model linking H&E images to gene expression in spatial omics. This is a work led by my PhD student, Ronald Xie (@RonaldXie1 )

Paper: https://t.co/HT1txYQ6wL
Code: https://t.co/rG31TXrx8U
More details: https://t.co/vwYeTUwsHa

2. Congfu, an innovative GNN architecture for predicting drug synergy. This is a work led by my Master student, Oleksii Tsepa !
Paper: https://t.co/7dBUtxJhKR
Code: https://t.co/gOw63uh6vI
More details: https://t.co/qY0covG3z5

Excited to reconnect with old friends and meet new ones! #AIforScience

[imgremlin @AlexTsepa]

Unfortunately, it's not about Westfold, but about my homeland

[The Gandalf @Samoilenko_I]

Where was Gondor when Westfold fell?

[Aran Komatsuzaki @arankomatsuzaki]

Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets

Present a collection of seven novel datasets, which cover ~100M molecules and >3K sparsely defined tasks, totaling >13B labels of both quantum and biological nature

https://t.co/9r9xJQFFFK

[NeurIPS Conference @NeurIPSConf]

Announcing the NeurIPS 2023 Competitions! We selected a total of 20 very strong proposals -- some of the competitions are completely new, others are familiar to the NeurIPS community.

More info on blog: https://t.co/1d3t1Aujxu
Full list on website: https://t.co/7A1l5pkyh7

[Demis Hassabis @demishassabis]

Our latest work in @Nature today: #AlphaDev discovered a new faster sorting algorithm that we open sourced to the main C++ library for all developers to use. This is just the beginning of AI being used to find many more efficiencies in code in future https://t.co/tfACG2zcN6

[imgremlin @AlexTsepa]

RT @BoWang87: Revolutionizing modern chemistry and drug discovery, #GNN focuses mostly on single graph representations. Yet, the study of m…