{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/compositionality-aware-graph2seq-learning","title":"Compositionality-Aware Graph2Seq Learning","arxiv_id":"2201.12178","date":"2022-01-28","proceeding":null,"authors":["Takeshi D. Itoh","Takatomi Kubo","Kazushi Ikeda"],"abstract":"Graphs are a highly expressive data structure, but it is often difficult for humans to find patterns from a complex graph. Hence, generating human-interpretable sequences from graphs have gained interest, called graph2seq learning. It is expected that the compositionality in a graph can be associated to the compositionality in the output sequence in many graph2seq tasks. Therefore, applying compositionality-aware GNN architecture would improve the model performance. In this study, we adopt the multi-level attention pooling (MLAP) architecture, that can aggregate graph representations from multiple levels of information localities. As a real-world example, we take up the extreme source code summarization task, where a model estimate the name of a program function from its source code. We demonstrate that the model having the MLAP architecture outperform the previous state-of-the-art model with more than seven times fewer parameters than it.","url_abs":"https://arxiv.org/abs/2201.12178v1","url_pdf":"https://arxiv.org/pdf/2201.12178v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"compositionality-aware-graph2seq-learning","repo_url":"https://github.com/itakeshi/mlap-graph2seq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"code-summarization-1","task_name":"Code Summarization"},{"task_slug":"code-summarization","task_name":"Source Code Summarization"}],"methods":[{"method_slug":"attention-pooling","method_name":"Attention Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}