{"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/gft-graph-foundation-model-with-transferable","title":"GFT: Graph Foundation Model with Transferable Tree Vocabulary","arxiv_id":"2411.06070","date":"2024-11-09","proceeding":null,"authors":["Zehong Wang","Zheyuan Zhang","Nitesh V Chawla","Chuxu Zhang","Yanfang Ye"],"abstract":"Inspired by the success of foundation models in applications such as ChatGPT, as graph data has been ubiquitous, one can envision the far-reaching impacts that can be brought by Graph Foundation Models (GFMs) with broader applications in the areas such as scientific research, social network analysis, drug discovery, and e-commerce. Despite the significant progress of pre-trained graph neural networks, there haven't been GFMs that can achieve desired performance on various graph-learning-related tasks. Building GFMs may rely on a vocabulary that encodes transferable patterns shared among different tasks and domains. Unlike image and text, defining such transferable patterns for graphs remains an open question. In this paper, we aim to bridge this gap by rethinking the transferable patterns on graphs as computation trees -- i.e., tree structures derived from the message-passing process. Based on this insight, we propose a cross-task, cross-domain graph foundation model named GFT, short for Graph Foundation model with transferable Tree vocabulary. By treating computation trees as tokens within the transferable vocabulary, GFT improves model generalization and reduces the risk of negative transfer. The theoretical analyses and extensive experimental studies have demonstrated the transferability of computation trees and shown the effectiveness of GFT across diverse tasks and domains in graph learning. The open source code and data are available at https://github.com/Zehong-Wang/GFT.","url_abs":"https://arxiv.org/abs/2411.06070v1","url_pdf":"https://arxiv.org/pdf/2411.06070v1.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":"gft-graph-foundation-model-with-transferable","repo_url":"https://github.com/zehong-wang/gft","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"graph-learning","task_name":"Graph Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2411.06070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06070"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/Zehong-Wang/GFT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zehong-wang/gft","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":4,"ran_draft_wrong":4,"ran_violates":2,"ran_honours":1,"unverified":14},"by_repo_kind":{"official":{"samples":24,"ran":10,"repositories":1},"community":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4dc1339e961ab500","entry":"batched_embedding","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4dc1339e961ab500"}},{"code_sha256_prefix":"4b4182a1077e1685","entry":"cdist","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b4182a1077e1685"}},{"code_sha256_prefix":"ba65976c1d96a7cb","entry":"creat_optimizer","repo":"thu-ml/GFT","repo_kind":"community","path":"LlamaGen/autoregressive/train/GFT_c2i.py","file_url":"https://github.com/thu-ml/GFT/blob/HEAD/LlamaGen/autoregressive/train/GFT_c2i.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ba65976c1d96a7cb"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":"Zehong-Wang/GFT","repo_kind":"official","path":"GFT/model/ft_model.py","file_url":"https://github.com/Zehong-Wang/GFT/blob/HEAD/GFT/model/ft_model.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"Zehong-Wang/GFT","repo_kind":"official","path":"GFT/model/ft_model.py","file_url":"https://github.com/Zehong-Wang/GFT/blob/HEAD/GFT/model/ft_model.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"4755d07ad4a639cb","entry":"gumbel_sample","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4755d07ad4a639cb"}},{"code_sha256_prefix":"f3232418205f7cbd","entry":"identity","repo":"Zehong-Wang/GFT","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/Zehong-Wang/GFT/blob/HEAD/GFT/model/vq.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3232418205f7cbd"}},{"code_sha256_prefix":"31974aebdb92319d","entry":"kmeans","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31974aebdb92319d"}},{"code_sha256_prefix":"702d64c397294ae2","entry":"laplace_smoothing","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"702d64c397294ae2"}},{"code_sha256_prefix":"690fb00cdadafe62","entry":"orthogonal_loss_fn","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"690fb00cdadafe62"}},{"code_sha256_prefix":"ecf368eff22730c4","entry":"sample_vectors_distributed","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ecf368eff22730c4"}},{"code_sha256_prefix":"5f925b34de0a38cb","entry":"ArxivFSSplitter","repo":"Zehong-Wang/GFT","repo_kind":"official","path":"GFT/dataset/task_constructor.py","file_url":"https://github.com/Zehong-Wang/GFT/blob/HEAD/GFT/dataset/task_constructor.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f925b34de0a38cb"}},{"code_sha256_prefix":"840cce4bf1e34557","entry":"CiteSplitter","repo":"Zehong-Wang/GFT","repo_kind":"official","path":"GFT/dataset/task_constructor.py","file_url":"https://github.com/Zehong-Wang/GFT/blob/HEAD/GFT/dataset/task_constructor.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"840cce4bf1e34557"}},{"code_sha256_prefix":"d8a07f536f522526","entry":"CosineSimCodebook","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d8a07f536f522526"}},{"code_sha256_prefix":"74f95d115c4d707c","entry":"EuclideanCodebook","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74f95d115c4d707c"}},{"code_sha256_prefix":"33b21e2fd12163eb","entry":"VectorQuantize","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"33b21e2fd12163eb"}},{"code_sha256_prefix":"352a58f5914509ef","entry":"binary_apr_func","repo":"Zehong-Wang/GFT","repo_kind":"official","path":"GFT/dataset/data_utils.py","file_url":"https://github.com/Zehong-Wang/GFT/blob/HEAD/GFT/dataset/data_utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"352a58f5914509ef"}},{"code_sha256_prefix":"c06eaa1bc9d830c1","entry":"binary_single_auc_func","repo":"Zehong-Wang/GFT","repo_kind":"official","path":"GFT/dataset/data_utils.py","file_url":"https://github.com/Zehong-Wang/GFT/blob/HEAD/GFT/dataset/data_utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c06eaa1bc9d830c1"}},{"code_sha256_prefix":"fda38ab65bb996a9","entry":"ema_inplace","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fda38ab65bb996a9"}},{"code_sha256_prefix":"6aa000a9e1b10057","entry":"filter_unnecessary_attrs","repo":"Zehong-Wang/GFT","repo_kind":"official","path":"GFT/dataset/process_datasets.py","file_url":"https://github.com/Zehong-Wang/GFT/blob/HEAD/GFT/dataset/process_datasets.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6aa000a9e1b10057"}},{"code_sha256_prefix":"1ae9c9bd82345553","entry":"flat_auc","repo":"Zehong-Wang/GFT","repo_kind":"official","path":"GFT/dataset/data_utils.py","file_url":"https://github.com/Zehong-Wang/GFT/blob/HEAD/GFT/dataset/data_utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ae9c9bd82345553"}},{"code_sha256_prefix":"9adcac32b9f87dfb","entry":"pack_one","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9adcac32b9f87dfb"}},{"code_sha256_prefix":"58d48991c9718144","entry":"refine_dataset","repo":"Zehong-Wang/GFT","repo_kind":"official","path":"GFT/dataset/process_datasets.py","file_url":"https://github.com/Zehong-Wang/GFT/blob/HEAD/GFT/dataset/process_datasets.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58d48991c9718144"}},{"code_sha256_prefix":"fe5ac93ea96ea352","entry":"span_node_and_edge_idx","repo":"Zehong-Wang/GFT","repo_kind":"official","path":"GFT/dataset/process_datasets.py","file_url":"https://github.com/Zehong-Wang/GFT/blob/HEAD/GFT/dataset/process_datasets.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fe5ac93ea96ea352"}},{"code_sha256_prefix":"95a567bd7c1ffdce","entry":"unpack_one","repo":"zehong-wang/gft","repo_kind":"official","path":"GFT/model/vq.py","file_url":"https://github.com/zehong-wang/gft/blob/HEAD/GFT/model/vq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95a567bd7c1ffdce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}