SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.16024 · 2024

HiGPT: Heterogeneous Graph Language Model

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.16024.json · badge: /api/ran/2402.16024.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
hkuds/higpt canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
find_all_linear_names Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from csm9493/efficient-llm-unlearning
pointer only · get_code("649fc48067a48529")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_model_pretrained Ran
ran; our contract draft was wrong, not the code
hkuds/higpt/higpt/model/GraphLlama.py
code served (permissive licence) · get_code("48e990ea1b99a86d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import json
import os
import tempfile
import shutil

torch.manual_seed(0)

# Create a temporary directory for the pretrain model
pretrain_dir = tempfile.mkdtemp()

# Create a minimal config.json file
config_dict = {
    "hidden_dim": 64,
    "num_layers": 2,
    "dropout": 0.1
}
config_path = os.path.join(pretrain_dir, 'config.json')
with open(config_path, 'w') as f:
    json.dump(config_dict, f)

# Create a minimal state dict and save it as .pkl
state_dict = {
    "layer1.weight": torch.randn(64, 64),
    "layer1.bias": torch.randn(64),
    "layer2.weight": torch.randn(64, 64),
    "layer2.bias": torch.randn(64),
    "logit_scale": torch.tensor(0.07)
}
pkl_path = os.path.join(pretrain_dir, 'model.pkl')
torch.save(state_dict, pkl_path)

# Create a minimal model class that accepts args and has load_state_dict
class MinimalGraphModel(nn.Module):
    def __init__(self, args):
        super().__init__()
        self.hidden_dim = args.hidden_dim
        self.num_layers = args.num_layers
        self.dropout = args.dropout
        self.layer1 = nn.Linear(64, 64)
        self.layer2 = nn.Linear(64, 64)
    
    def forward(self, x):
        return x

ARGS = {
    "model_name": MinimalGraphModel,
    "pretrain_model_path": pretrain_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
transfer_param_tograph Ran
ran; our contract draft was wrong, not the code
hkuds/higpt/higpt/model/GraphLlama.py
code served (permissive licence) · get_code("17582c82f42bd6a2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned MinimalGNN. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Build a minimal GNN module
class MinimalGNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Build a minimal clip_graph that has a gnn attribute
class MinimalCLIPGraph(nn.Module):
    def __init__(self):
        super().__init__()
        self.gnn = MinimalGNN()
    
    def forward(self, x):
        return self.gnn(x)

# Create instances
clip_graph = MinimalCLIPGraph()
gnn = MinimalGNN()

ARGS = {
    "clip_graph": clip_graph,
    "gnn": gnn
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MinimalGNN — a MinimalGNN output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MinimalGNN output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
find_all_linear_names 22 other papers
4 dated earlier, 17 later, 1 same year, order not determinable
2308.09936 (2023-08)
BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions
2310.13023 (2023-10)
GraphGPT: Graph Instruction Tuning for Large Language Models
2311.13194 (2023-11)
Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs
and 19 more not named here
load_model_pretrained 1 other paper
1 dated earlier
2310.13023 (2023-10)
GraphGPT: Graph Instruction Tuning for Large Language Models
transfer_param_tograph 1 other paper
1 dated earlier
2310.13023 (2023-10)
GraphGPT: Graph Instruction Tuning for Large Language Models

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

Heterogeneous graph learning aims to capture complex relationships and diverse relational semantics among entities in a heterogeneous graph to obtain meaningful representations for nodes and edges. Recent advancements in heterogeneous graph neural networks (HGNNs) have achieved state-of-the-art performance by considering relation heterogeneity and using specialized message functions and aggregation rules. However, existing frameworks for heterogeneous graph learning have limitations in generalizing across diverse heterogeneous graph datasets. Most of these frameworks follow the "pre-train" and "fine-tune" paradigm on the same dataset, which restricts their capacity to adapt to new and unseen data. This raises the question: "Can we generalize heterogeneous graph models to be well-adapted to diverse downstream learning tasks with distribution shifts in both node token sets and relation type heterogeneity?'' To tackle those challenges, we propose HiGPT, a general large graph model with Heterogeneous graph instruction-tuning paradigm. Our framework enables learning from arbitrary heterogeneous graphs without the need for any fine-tuning process from downstream datasets. To handle distribution shifts in heterogeneity, we introduce an in-context heterogeneous graph tokenizer that captures semantic relationships in different heterogeneous graphs, facilitating model adaptation. We incorporate a large corpus of heterogeneity-aware graph instructions into our HiGPT, enabling the model to effectively comprehend complex relation heterogeneity and distinguish between various types of graph tokens. Furthermore, we introduce the Mixture-of-Thought (MoT) instruction augmentation paradigm to mitigate data scarcity by generating diverse and informative instructions. Through comprehensive evaluations, our proposed framework demonstrates exceptional performance in terms of generalization performance.

For agents

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

get_harvested_code_for_paper("2402.16024")
get_code_for_paper("2402.16024")
have("2402.16024")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.16024.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.16024.svg)](https://syntology.ai/paper/2402.16024)

Connect an agent — have() is free.