SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.03195 · 2024

RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning

arXiv · PDF · Open in the Atlas

Code that ran

10 of 15 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 8 failures of our instrument; 5 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/2408.03195.json · badge: /api/ran/2408.03195.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
JasonZhujp/RELIEF canonical (classifier label)
classifier basis: census
10 ran · 5 no recorded run
FunctionStatusWhere it lives
act Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JasonZhujp/RELIEF/node_level/model.py
pointer only (licence: NONE) · get_code("4f889a3f511e5688")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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.

compute_acc_f1 Ran
ran; our contract draft was wrong, not the code
JasonZhujp/RELIEF/node_level/base.py
pointer only (licence: NONE) · get_code("bdacd4343b5f189b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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.

compute_auc Ran
ran; our contract draft was wrong, not the code
JasonZhujp/RELIEF/graph_level/base.py
pointer only (licence: NONE) · get_code("7704b623591b1777")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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.

graph_data_obj_to_nx_simple Ran
ran, honoured the contract we drafted
JasonZhujp/RELIEF/graph_level/loader.py
pointer only (licence: NONE) · get_code("287484b87212f47d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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.

index_new_batch Ran
ran; our contract draft was wrong, not the code
JasonZhujp/RELIEF/graph_level/util.py
pointer only (licence: NONE) · get_code("2df6ffa7e9fcd02e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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.

niceprint Ran
ran; our contract draft was wrong, not the code
JasonZhujp/RELIEF/graph_level/util.py
pointer only (licence: NONE) · get_code("9f4264652469074d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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.

reshape_reward Ran
ran; our contract draft was wrong, not the code
JasonZhujp/RELIEF/graph_level/reward.py
pointer only (licence: NONE) · get_code("2890d744d2853964")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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.

reward_reshape Ran
ran, violated the contract we drafted
JasonZhujp/RELIEF/graph_level/reward.py
pointer only (licence: NONE) · get_code("84ca8cb0e314e41b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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.

reward_scaling Ran
ran; our contract draft was wrong, not the code
JasonZhujp/RELIEF/graph_level/reward.py
pointer only (licence: NONE) · get_code("e55364295e61d890")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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.

seed_everything Ran
ran; our contract draft was wrong, not the code
JasonZhujp/RELIEF/node_level/pretrain_gppt.py
pointer only (licence: NONE) · get_code("310641cfd279407f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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.

load4link_prediction_single_graph Not yet run
unverified (harvested, no recorded run)
JasonZhujp/RELIEF/node_level/pretrain_gppt.py
pointer only (licence: NONE) · get_code("456c37ccc04762a6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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. No invocation recorded.

load4node Not yet run
unverified (harvested, no recorded run)
JasonZhujp/RELIEF/node_level/preprocess.py
pointer only (licence: NONE) · get_code("e59aa76a99f6ad62")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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. No invocation recorded.

split_subgraph Not yet run
unverified (harvested, no recorded run)
JasonZhujp/RELIEF/node_level/preprocess.py
pointer only (licence: NONE) · get_code("9ef4f85d40909997")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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. No invocation recorded.

subgraph_node_num Not yet run
unverified (harvested, no recorded run)
JasonZhujp/RELIEF/node_level/preprocess.py
pointer only (licence: NONE) · get_code("da3dbf71c8d03d72")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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. No invocation recorded.

tasknet_loss Not yet run
unverified (harvested, no recorded run)
JasonZhujp/RELIEF/node_level/base.py
pointer only (licence: NONE) · get_code("53d5135d0826a45f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JasonZhujp/RELIEF when it was checked. 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. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 14 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
graph_data_obj_to_nx_simple 9 other papers
9 dated earlier
1905.12265 (2019-05)
Strategies for Pre-training Graph Neural Networks
2302.04451 (2023-02)
Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion
2306.07812 (2023-06)
Automated 3D Pre-Training for Molecular Property Prediction
and 6 more not named here

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

The advent of the "pre-train, prompt" paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in Natural Language Processing (NLP). Initial graph prompt tuning approaches tailored specialized prompting functions for Graph Neural Network (GNN) models pre-trained with specific strategies, such as edge prediction, thus limiting their applicability. In contrast, another pioneering line of research has explored universal prompting via adding prompts to the input graph's feature space, thereby removing the reliance on specific pre-training strategies. However, the necessity to add feature prompts to all nodes remains an open question. Motivated by findings from prompt tuning research in the NLP domain, which suggest that highly capable pre-trained models need less conditioning signal to achieve desired behaviors, we advocate for strategically incorporating necessary and lightweight feature prompts to certain graph nodes to enhance downstream task performance. This introduces a combinatorial optimization problem, requiring a policy to decide 1) which nodes to prompt and 2) what specific feature prompts to attach. We then address the problem by framing the prompt incorporation process as a sequential decision-making problem and propose our method, RELIEF, which employs Reinforcement Learning (RL) to optimize it. At each step, the RL agent selects a node (discrete action) and determines the prompt content (continuous action), aiming to maximize cumulative performance gain. Extensive experiments on graph and node-level tasks with various pre-training strategies in few-shot scenarios demonstrate that our RELIEF outperforms fine-tuning and other prompt-based approaches in classification performance and data efficiency. The code is available at https://github.com/JasonZhujp/RELIEF.

For agents

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

get_harvested_code_for_paper("2408.03195")
get_code_for_paper("2408.03195")
have("2408.03195")

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

curl https://syntology.ai/api/ran/2408.03195.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.03195.svg)](https://syntology.ai/paper/2408.03195)

Connect an agent — have() is free.