SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.15569 · IJCAI · 2024

Efficient Tuning and Inference for Large Language Models on Textual Graphs

Siliang Tang, Haizhou Shi, Yun Zhu, Yaoke Wang

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 1 has no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2401.15569.json · badge: /api/ran/2401.15569.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
ZhuYun97/ENGINE marked official in Papers with Code
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
PMLP_Encoder Ran
ran on a synthesized input
ZhuYun97/ENGINE/models/encoder.py
pointer only (licence: NONE) · get_code("ef60fef76b9b161f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZhuYun97/ENGINE 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.

get_activation Ran
ran; our contract draft was wrong, not the code
ZhuYun97/ENGINE/models/encoder.py
pointer only (licence: NONE) · get_code("d9708b884df48ddc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZhuYun97/ENGINE 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.

get_norm Ran
ran; our contract draft was wrong, not the code
ZhuYun97/ENGINE/models/encoder.py
pointer only (licence: NONE) · get_code("effa674fb5eabfa4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZhuYun97/ENGINE 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.

Register Not yet run
unverified (harvested, no recorded run)
ZhuYun97/ENGINE/models/encoder.py
pointer only (licence: NONE) · get_code("68a9d8ee9a9a5495")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZhuYun97/ENGINE 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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
get_activation
brick of this paper's assembly: helper
1 other paper
1 later
2412.21151 (2024-12)
PyG-SSL: A Graph Self-Supervised Learning Toolkit

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

Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder and a subsequent graph neural network (GNN) to solve this problem. In light of recent advancements in large language models (LLMs), it is apparent that integrating LLMs for enhanced textual encoding can substantially improve the performance of textual graphs. Nevertheless, the efficiency of these methods poses a significant challenge. In this paper, we propose ENGINE, a parameter-and memory-efficient fine-tuning method for textual graphs with an LLM encoder. The key insight is to combine the LLMs and GNNs through a tunable side structure, which significantly reduces the training complexity without impairing the joint model's capacity. Extensive experiments on textual graphs demonstrate our method's effectiveness by achieving the best model performance, meanwhile having the lowest training cost compared to previous methods. Moreover, we introduce two variants with caching and dynamic early exit to further enhance training and inference speed. Specifically, caching accelerates ENGINE's training by 12x, and dynamic early exit achieves up to 5x faster inference with a negligible performance drop (at maximum 1.17% relevant drop across 7 datasets). Our codes are available at: https://github.com/ZhuYun97/ENGINE

For agents

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

get_harvested_code_for_paper("2401.15569")
get_code_for_paper("2401.15569")
have("2401.15569")

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

curl https://syntology.ai/api/ran/2401.15569.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.15569.svg)](https://syntology.ai/paper/2401.15569)

Connect an agent — have() is free.