Papers › TREE-G: Decision Trees Contesting Graph Neural Networks

TREE-G: Decision Trees Contesting Graph Neural Networks

6 Jul 2022arXiv:2207.02760archive 2025-07-28

Maya Bechler-Speicher, Amir Globerson, Ran Gilad-Bachrach

When dealing with tabular data, models based on decision trees are a popular choice due to their high accuracy on these data types, their ease of application, and explainability properties. However, when it comes to graph-structured data, it is not clear how to apply them effectively, in a way that incorporates the topological information with the tabular data available on the vertices of the graph. To address this challenge, we introduce TREE-G. TREE-G modifies standard decision trees, by introducing a novel split function that is specialized for graph data. Not only does this split function incorporate the node features and the topological information, but it also uses a novel pointer mechanism that allows split nodes to use information computed in previous splits. Therefore, the split function adapts to the predictive task and the graph at hand. We analyze the theoretical properties of TREE-G and demonstrate its benefits empirically on multiple graph and vertex prediction benchmarks. In these experiments, TREE-G consistently outperforms other tree-based models and often outperforms other graph-learning algorithms such as Graph Neural Networks (GNNs) and Graph Kernels, sometimes by large margins. Moreover, TREE-Gs models and their predictions can be explained and visualized

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mayabechlerspeicher/tree-g officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 9 ran (0 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran
1unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from mayabechlerspeicher/tree-g. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

mayabechlerspeicher/tree-g official repository 10 samples, 9 ran (0 instrument-failed) · 1 unverified
auc_pytorch eval_utils/metrics.py ran MIT (permissive) · f6edee7478a3f851 · report fixture: signature y:Tensor/1/float, out:Tensor/2/float · returned float · level recorded 2026-09-25
balance_data utils.py ran MIT (permissive) · c5fb1e62e9b6b32b · report fixture: signature X:ndarray/2/float, y:ndarray/1/int · returned tuple · level recorded 2026-09-25
create_logger in 172 papers eval_utils/general.py ran MIT (permissive) · cfdf94fad1b8a3fe · report fixture: signature log_dir:str/0/str, log_name:str/0/str, dump:bool/0/bool · returned RootLogger · level recorded 2026-09-25
get_balanced_data_for_class utils.py ran MIT (permissive) · b35b5897fe219832 · report fixture: signature class_i:int/0/int, X:ndarray/2/float, y:ndarray/1/int · returned tuple · level recorded 2026-09-25
intersect in 33 papers treeg/node_treeg/tree_node_learner_node_level.py ran fingerprinted MIT (permissive) · d9b7c68d3b67de6f · report fixture: signature lst1:list/1/int, lst2:list/1/int · returned list · level recorded 2026-09-25
load_json in 344 papers eval_utils/general.py ran MIT (permissive) · f753e3699554e87a · report fixture: signature json_filename:str/0/str · returned dict · level recorded 2026-09-25
load_pickle in 115 papers eval_utils/general.py ran MIT (permissive) · 17a866b6340f7ad0 · report fixture: signature pkl_filename:str/0/str · returned dict · level recorded 2026-09-25
load_pickle_from_path utils.py ran MIT (permissive) · dfeb71444a0b6511 · report fixture: signature file_path_from_root:str/0/str · returned dict · level recorded 2026-09-25
round_acc eval_utils/metrics.py ran fingerprinted MIT (permissive) · 69b43268d8037d42 · report fixture: signature y:ndarray/1/int, y_pred:ndarray/1/float · returned float64 · level recorded 2026-09-25

Tasks

Graph ClassificationGraph LearningGraph RegressionNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification D&D TREE-G Accuracy 76.2% #39 of 53 Archive leaderboard report
Graph Classification ENZYMES TREE-G Accuracy 59.6 #30 of 54 Archive leaderboard report
Graph Classification HIV dataset TREE-G Accuracy 83.5 #4 of 5 Archive leaderboard report
Graph Classification IMDb-B TREE-G Accuracy 73% #37 of 51 Archive leaderboard report
Graph Classification IMDb-M TREE-G Accuracy 56.4% #3 of 36 Archive leaderboard report
Graph Classification MUTAG TREE-G Accuracy 91.1% #16 of 74 Archive leaderboard report
Graph Classification Mutagenicity TREE-G Accuracy 83 #1 of 5 Archive leaderboard report
Graph Classification NCI1 TREE-G Accuracy 75.9% #50 of 69 Archive leaderboard report
Graph Classification PROTEINS TREE-G Accuracy 75.6 #63 of 103 Archive leaderboard report
Graph Classification PTC TREE-G Accuracy 59.1% #36 of 37 Archive leaderboard report
Node Classification Citeseer TREE-G Accuracy 74.5 #28 of 71 Archive leaderboard report
Node Classification Cora: fixed 20 node per class TREE-G Accuracy 83.5 #5 of 9 Archive leaderboard report
Node Classification Pubmed TREE-G Accuracy 78.0 #57 of 70 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections