PATTON : Language Model Pretraining on Text-Rich Networks

Qi Zhu, Jiawei Han, Yu Zhang, Yu Meng, Wentao Zhang, Jin Bowen, Xinyang Zhang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 2 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.

Repositories linked to this paper

• PeterGriffinJin/Patton

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

Abstract

A real-world text corpus sometimes comprises not only text documents, but also semantic links between them (e.g., academic papers in a bibliographic network are linked by citations and co-authorships). Text documents and semantic connections form a text-rich network, which empowers a wide range of downstream tasks such as classification and retrieval. However, pretraining methods for such structures are still lacking, making it difficult to build one generic model that can be adapted to various tasks on text-rich networks. Current pretraining objectives, such as masked language modeling, purely model texts and do not take interdocument structure information into consideration. To this end, we propose our PretrAining on TexT-Rich NetwOrk framework PATTON. PATTON 1 includes two pretraining strategies: network-contextualized masked language modeling and masked node prediction, to capture the inherent dependency between textual attributes and network structure. We conduct experiments on four downstream tasks in five datasets from both academic and e-commerce domains, where PATTON outperforms baselines significantly and consistently.

For agents

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

get_harvested_code_for_paper("2305.12268")
get_code_for_paper("2305.12268")
have("2305.12268")

Connect an agent — have() is free.