Summary of Mint: Multi-network Training For Transfer Learning on Temporal Graphs, by Kiarash Shamsi et al.
MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs
by Kiarash Shamsi, Tran Gia Bao Ngo, Razieh Shirzadkhani, Shenyang Huang, Farimah Poursafaei, Poupak Azad, Reihaneh Rabbany, Baris Coskunuzer, Guillaume Rabusseau, Cuneyt Gurcan Akcora
First submitted to arxiv on: 14 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel pre-training approach called Temporal Multi-network Training (MiNT) is introduced to learn from multiple temporal networks and improve their transferability to unobserved networks. The approach learns from up to 64 networks and achieves state-of-the-art results in zero-shot inference, surpassing models individually trained on each network. The findings demonstrate that increasing the number of pre-training networks significantly improves transfer performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Learning patterns in dynamic networks is a crucial task. A new study explores how well a model can learn from many networks and use this knowledge to predict interactions in unseen networks. To do this, researchers developed a method called Temporal Multi-network Training (MiNT). They used 84 different networks to train the model and tested it on 20 new networks. The results were amazing – the model did better than models that learned only from one network. When they used more networks to train the model, the performance got even better. |
Keywords
» Artificial intelligence » Inference » Transferability » Zero shot
