Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions

September 23, 2019 ยท Entered Twilight ยท ๐Ÿ› PLoS ONE

๐ŸŒ… TWILIGHT: Old Age
Predates the code-sharing era โ€” a pioneer of its time

"Last commit was 5.0 years ago (โ‰ฅ5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: Github, LICENSE.md, README.md, SocialEvolution.zip, SocialEvolution, data_loader.py, dyrep.py, encoder.py, example_data_loader.py, freq.py, github_data_loader.py, main.py, social_data_loader.py, utils.py

Authors Boris Knyazev, Carolyn Augusta, Graham W. Taylor arXiv ID 1909.10367 Category stat.ML: Machine Learning (Stat) Cross-listed cs.AI, cs.LG Citations 31 Venue PLoS ONE Repository https://github.com/uoguelph-mlrg/LDG โญ 101 Last Checked 3 months ago
Abstract
Reasoning about graphs evolving over time is a challenging concept in many domains, such as bioinformatics, physics, and social networks. We consider a common case in which edges can be short term interactions (e.g., messaging) or long term structural connections (e.g., friendship). In practice, long term edges are often specified by humans. Human-specified edges can be both expensive to produce and suboptimal for the downstream task. To alleviate these issues, we propose a model based on temporal point processes and variational autoencoders that learns to infer temporal attention between nodes by observing node communication. As temporal attention drives between-node feature propagation, using the dynamics of node interactions to learn this key component provides more flexibility while simultaneously avoiding issues associated with human-specified edges. We also propose a bilinear transformation layer for pairs of node features instead of concatenation, typically used in prior work, and demonstrate its superior performance in all cases. In experiments on two datasets in the dynamic link prediction task, our model often outperforms the baseline model that requires a human-specified graph. Moreover, our learned attention is semantically interpretable and infers connections similar to actual graphs.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning (Stat)

๐Ÿ”ฎ ๐Ÿ”ฎ The Ethereal

Layer Normalization

Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. Hinton

stat.ML ๐Ÿ› arXiv ๐Ÿ“š 12.0K cites 9 years ago