Michael Diskin (@michael_diskin) profile picture

DL researcher somewhere ex @YandexResearch Sporadically teaching and studying at @CS_HSE

World
Joined September 2013
Photo by Michael Diskin (@michael_diskin)Photo by Michael Diskin (@michael_diskin)Photo by Michael Diskin (@michael_diskin)Photo by Michael Diskin (@michael_diskin)Photo by Michael Diskin (@michael_diskin)Photo by Michael Diskin (@michael_diskin)Photo by Michael Diskin (@michael_diskin)Photo by Michael Diskin (@michael_diskin)Photo by Michael Diskin (@michael_diskin)
Heterophilous graphs, in which edges connect dissimilar nodes, are challenging for GNNs. In our #iclr2023 paper, we propose a new benchmark of 5 structurally diverse heterophilous graph datasets. Read more in this post by Oleg Platonov and @LProkhorenkova research.yandex.com/blog/int…
3
10
1,258
Michael Diskin retweeted
We present SWARM, an efficient algorithm for model-parallel training across the Internet (e.g. with volunteers). Key advantages: 💎 Fault-tolerant ⚖️ Self-balancing on slow GPUs/networks 🐌 Works in low-bandwidth setups 📜 arxiv.org/abs/2301.11913 🖥️ github.com/yandex-research/s…
11
61
10
260
53,880
Want to assess uncertainty and robustness in Self-Driving, Translation and Weather Prediction? Check out our #NeurIPS2021 paper: Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks: tinyurl.com/2p8833dp See poster B1 at DBT, session 4 room 2
1
6
1
12
At #NeurIPS2021, we will showcase our latest research in a variety of ML-related areas, with a total of eight papers, two benchmarks and one demonstration accepted at the conference. You can find the full details in the link below: research.yandex.com/news/pap…
4
4
Michael Diskin retweeted
In our latest work, we propose DeDLOC — a method for efficient collaborative training. This approach allowed us to pretrain sahajBERT (a Bengali-language ALBERT) together with the help of volunteers from the community! (1/10) arxiv.org/abs/2106.10207 github.com/yandex-research/D…
3
39
10
132