SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.12787 · 2022

GRPE: Relative Positional Encoding for Graph Transformer

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
lenscloth/grpe canonical 3 of 6
FunctionStatusWhere it lives
evaluate Ran lenscloth/grpe/zinc.py
code served (permissive licence) · get_code("9266294d3f2bade7")
is_left_better Ran lenscloth/grpe/gpp.py
code served (permissive licence) · get_code("13f0b879ee9b94c4")
train Ran lenscloth/grpe/zinc.py
code served (permissive licence) · get_code("9ec5aa5e7b77d9b7")
gather_uneven_tensors Not yet run lenscloth/grpe/grpe/distributed.py
code served (permissive licence) · get_code("9ff14674677c2429")
load_pretrained_fingerprint Not yet run lenscloth/grpe/grpe/pretrained.py
code served (permissive licence) · get_code("4b3aa1f322c9bfcb")
train Not yet run lenscloth/grpe/gpp.py
code served (permissive licence) · get_code("79c9fa759ce09d31")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a novel positional encoding for learning graph on Transformer architecture. Existing approaches either linearize a graph to encode absolute position in the sequence of nodes, or encode relative position with another node using bias terms. The former loses preciseness of relative position from linearization, while the latter loses a tight integration of node-edge and node-topology interaction. To overcome the weakness of the previous approaches, our method encodes a graph without linearization and considers both node-topology and node-edge interaction. We name our method Graph Relative Positional Encoding dedicated to graph representation learning. Experiments conducted on various graph datasets show that the proposed method outperforms previous approaches significantly. Our code is publicly available at https://github.com/lenscloth/GRPE.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2201.12787")
get_code_for_paper("2201.12787")
have("2201.12787")

Connect an agent — have() is free.