📣 We’re excited to announce the Graph Positional and Structural Encoder (GPSE) 🌐: The first graph encoder that learns highly transferable, unified representations for multiple positional encodings!
📜 Paper: https://t.co/8roPJA2Mvt
🛠 Code: https://t.co/eTzPNXvWu1
👇 🧵[1/11]
You can find all the 64 accepted papers (pdf) @CoLLAs_Conf#CoLLAs2022 and their video presentations here: https://t.co/Xl64QpPpuK. You can watch these video presentations even if you have not registered to attend the conference!
🧵1/3 In the past 2 years, models posted on the OGB-molHIV datasets saw their test score increase, but val decrease.
Models never stay on top of benchmarks for long. But, I'm proud to say that our models, PNA and DGN, have held the top spot on the val roc-aucfor almost 2 years!
Electric cars are cool but they seem to have a lot of serious flaws like having to rebuild the distribution system and reliance on some rare minerals. Making fuel from algae seems important to explore
Algae can be turned into fuels like ethanol, diesel and jet fuel — but the process has always been prohibitively expensive. Now, researchers are using AI to augment algal growth, potentially turning these blue-green bacterial blooms into biofuel booms. https://t.co/V7kMxcZFyr
@pickover Looks like the flares happen mostly on the "tropics" parallels in this picture. I wonder if it's a coincidence or there's some physics explaining this
Thrilled that our paper "Understanding over-squashing and bottlenecks on graphs via curvature" has been accepted for an oral presentation at #ICLR2022! Big thank you to the team @Francesco_dgv @b_p_chamberlain @epomqo@mmbronstein (https://t.co/LH6SuzkK10)
This Tuesday in LoGaG @Francesco_dgv@jctopping and @b_p_chamberlain present their "Understanding over-squashing and bottlenecks on graphs via curvature" https://t.co/BUBEqdXiqz - an absolute super-star paper from #iclr2022!🚀
Join the meeting here: https://t.co/9fxz75txpY
1/2
It's amazing what can be found in Conway's #GameOfLife ..
.. with a few 'technical upgrades' expanding the parameter-space and running it on a GPU!
- Continuous State
- Multiple Neighborhoods
- Multi-channel (RGB) space
- Cross-channel coupling
- Dynamic Neighborhood Selection
Twitter is so frustrating to navigate! I just saw this amazing tweet, hit the wrong button, hit back, cant find the tweet again in my feed! how can this happen? how to prevent this??
Equifax is selling access to people's salary data as part of an "employment verification solution" that includes:
Previous annual salaries
Previous weekly paycheck amounts
Previous addresses
Who accessed the report in the last 24 hours
Etc.
https://t.co/9RyO4I2ivf
[🧠 collective intelligence 🧠] I've been intrigued by the cellular automata (CA) concept for a long time, and by the potential, mutually beneficial interaction between CAs and deep learning, so I decided to dig a bit deeper. Here are some interesting resources I found:
1/🧵
Is chaos actually hard to predict? For NeurIPS this year I made a database of 131 known strange attractors, and trained state-of-the-art forecasting models on each one, to try to figure this out (1/N):
Paper: https://t.co/6tZ9MGAAI3
Dataset + Code: https://t.co/EpK4ZfWTEF
Join the GraphML reading group this Tuesday for "Rethinking Graph Transformers with Spectral Attention" https://t.co/xsD0JAefaa presented by authors @dom_beaini@KreuzerDevin!
With WL. Hamiliton @vincentmillions@TOSSOUPrudencio
The Zoom is here: https://t.co/A53uU31jCp
1/2
@math3ma Do you know if the similar statement with quantum states and Von Neuman entropy is true? seems like it would follow if there is a quantum version of Faddeev-Leinster