CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts

Di Jin; Dongxiao He; Jitao Zhao; Peiyuan Li; Weixiong Zhang; Yongqi Huang

arxiv: 2605.15888 · v2 · pith:WS5AECQHnew · submitted 2026-05-15 · 💻 cs.LG · cs.AI

CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts

Peiyuan Li , Yongqi Huang , Jitao Zhao , Dongxiao He , Di Jin , Weixiong Zhang This is my paper

Pith reviewed 2026-05-20 20:10 UTC · model grok-4.3

classification 💻 cs.LG cs.AI

keywords heterogeneous graphprompt learningcross-domainexpert networkmeta-pathfew-shotrouting

0 comments

The pith

CHoE adapts heterogeneous graph prompt learning to cross-domain settings using structure-conditioned experts and routing.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces CHoE to extend heterogeneous graph prompt learning to cross-domain scenarios where pre-training and downstream data distributions differ. It trains structure-conditioned experts on meta-path views from the source domain during pre-training. During prompt tuning it uses structure-aware expert routing and load balancing to select compatible experts for the target domain, along with a prompt-based semantic fusion module to combine multi-view representations. This setup aims to prevent the performance degradation seen in prior in-domain only methods. If true, it would enable more practical use of pre-trained graph models in real-world settings with domain shifts and limited labels.

Core claim

The authors claim that CHoE, built on an expert network, trains structure-conditioned experts during pre-training and applies structure-aware expert routing with load balancing during prompt tuning, plus semantic fusion, resulting in consistent improvements for few-shot cross-domain heterogeneous graph prompt learning over baselines.

What carries the argument

Structure-conditioned experts that are trained on specific meta-path views and routed based on structural compatibility to adapt to new domains.

If this is right

CHoE improves performance in few-shot cross-domain applications.
It outperforms all baseline approaches in such settings.
The routing mechanism helps handle distribution shifts without major degradation.
Semantic fusion integrates representations from multiple views effectively.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The expert routing idea might apply to homogeneous graphs or other data types with structural shifts.
It could reduce reliance on collecting target domain data for pre-training.
Testing the load balancing in scenarios with many experts would check for scalability.

Load-bearing premise

Structure-conditioned experts from the source domain can be routed to handle shifts in target domains without significant performance loss or expert collapse.

What would settle it

If on a cross-domain test set the performance of CHoE with structure-aware routing equals that of a version with random expert selection, the value of the conditioning and routing would be called into question.

Figures

Figures reproduced from arXiv: 2605.15888 by Di Jin, Dongxiao He, Jitao Zhao, Peiyuan Li, Weixiong Zhang, Yongqi Huang.

**Figure 2.** Figure 2: Overall framework of CHoE. In the pre-training stage, we adopt a generative framework to train an encoder. In the fine-tuning stage, [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗

**Figure 3.** Figure 3: Cross-domain node classification over four datasets under different shot settings. [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗

**Figure 4.** Figure 4: Hyperparameter analysis. Sensitivity of the balancing co [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗

read the original abstract

Heterogeneous Graph Prompt Learning (HGPL)has emerged as a promising paradigm for bridging the gap between the objectives of pre-training foundation models and their downstream applications in heterogeneous graph settings. However, existing HGPL methods are primarily designed for in-domain scenarios, whereas real-world deployments often span multiple domains, and the data used for pre-training and downstream tasks may originate from different distributions. Consequently, the applicability of current HGPL approaches is limited to in-domain settings, and their performance typically degrades when application domains shift. To address this serious limitation, we develop CHoE, a cross-domain HGPL method built upon an expert network. During pre-training, we introduce and train structure-conditioned experts, and during prompt tuning, we adopt a structure-aware expert routing and load balancing mechanism to select structurally compatible experts for each meta-path view. In addition, we design a prompt-based semantic fusion module to integrate representations across multiple views for downstream prediction. Extensive experiments show that CHoE consistently improves performance in few-shot cross-domain applications, outperforming all baseline approaches.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

CHoE adds structure-conditioned experts plus routing and load balancing to make heterogeneous graph prompt learning work across domains, but the abstract gives almost no experimental detail to judge whether the routing actually handles structural shifts.

read the letter

The main point is that this paper takes existing heterogeneous graph prompt learning and tries to make it cross-domain by training structure-conditioned experts on source meta-path views, then routing them with structure awareness and load balancing during prompt tuning, followed by semantic fusion across views. That combination is the concrete addition over prior in-domain HGPL work. It targets a real deployment issue where pre-training data and downstream data come from different distributions, and the abstract claims consistent gains in few-shot cross-domain settings over baselines. If the full experiments include diverse domain pairs and ablations on the routing step, this could be a useful practical tweak for people already using prompt-based graph models. The method description itself looks straightforward and builds directly on standard expert and routing ideas without overcomplicating the setup. Credit for spelling out the pre-training versus prompt-tuning split and for including load balancing to avoid obvious collapse modes. The soft spot is that the abstract supplies no numbers, no dataset names, no ablation tables, and no mention of how they quantify structural compatibility between source and target meta-paths. Without that, it is hard to tell whether the reported outperformance comes from the routing actually picking compatible experts or from something simpler like better fusion. The stress-test concern about mismatch leading to silent degradation or collapse is reasonable to raise here; the abstract does not show evidence that the structure-aware router maintains performance when meta-path statistics differ substantially, so that assumption remains untested in the summary we have. A reader working on graph transfer or foundation models would find the architecture description and the few-shot cross-domain framing useful to think about, even if they end up adapting the routing part. The paper is coherent on its own terms and engages the relevant literature on HGPL and expert networks, so it is worth a serious referee. I would send it to peer review and ask the authors to add concrete routing diagnostics and cross-domain structural similarity metrics in revision.

Referee Report

2 major / 1 minor

Summary. The paper proposes CHoE, a cross-domain heterogeneous graph prompt learning method. It trains structure-conditioned experts during pre-training on source-domain meta-path views and, during prompt tuning, applies structure-aware expert routing plus load balancing to select compatible experts for target domains, followed by prompt-based semantic fusion across views. The central claim is that this yields consistent performance gains over baselines in few-shot cross-domain heterogeneous graph tasks.

Significance. If the routing mechanism reliably transfers without expert collapse or degradation under domain shift, the work would meaningfully extend heterogeneous graph prompt learning beyond in-domain settings to practical multi-domain deployments, where pre-training and downstream data distributions commonly differ.

major comments (2)

[Abstract] The abstract states that CHoE 'consistently improves performance in few-shot cross-domain applications, outperforming all baseline approaches,' yet supplies no quantitative metrics, dataset names, ablation results, or statistical significance tests. This directly affects assessment of whether the empirical support for the central claim is robust.
[Method (prompt tuning and routing)] The structure-aware expert routing and load-balancing mechanism (described in the prompt-tuning stage) lacks any reported measure or ablation of structural compatibility between source and target meta-paths, such as meta-path type/length overlap or basic graph statistics. Without this, it is unclear whether the no-degradation assumption holds when domains differ substantially, which is load-bearing for the cross-domain transfer claim.

minor comments (1)

[Abstract] The abstract contains a typographical error: 'HGPL)has' should be 'HGPL has'.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. The comments highlight opportunities to strengthen the presentation of empirical results and the validation of our cross-domain assumptions. We address each major comment below and outline the revisions we will make.

read point-by-point responses

Referee: [Abstract] The abstract states that CHoE 'consistently improves performance in few-shot cross-domain applications, outperforming all baseline approaches,' yet supplies no quantitative metrics, dataset names, ablation results, or statistical significance tests. This directly affects assessment of whether the empirical support for the central claim is robust.

Authors: We agree that the abstract would be more informative with specific quantitative details. In the revised manuscript we will update the abstract to include representative performance gains (e.g., average accuracy or AUC improvements), the primary datasets used, and reference to statistical significance testing across the few-shot cross-domain settings. revision: yes
Referee: [Method (prompt tuning and routing)] The structure-aware expert routing and load-balancing mechanism (described in the prompt-tuning stage) lacks any reported measure or ablation of structural compatibility between source and target meta-paths, such as meta-path type/length overlap or basic graph statistics. Without this, it is unclear whether the no-degradation assumption holds when domains differ substantially, which is load-bearing for the cross-domain transfer claim.

Authors: We acknowledge that direct measures of structural compatibility are not reported in the current version. While our overall experimental results show consistent gains under domain shift, we will add a dedicated analysis subsection that quantifies meta-path type/length overlap and basic graph statistics (e.g., node/edge degree distributions) between the source and target domains used in our experiments, together with an ablation on how these factors correlate with routing behavior and performance. revision: yes

Circularity Check

0 steps flagged

No circularity: CHoE is presented as an independent architectural construction validated by experiments.

full rationale

The abstract and description frame CHoE as a new method with structure-conditioned experts trained during pre-training and structure-aware routing plus semantic fusion applied during prompt tuning. No equations, derivations, or predictions are described that reduce by construction to fitted inputs or self-citations. The central claims rest on empirical improvements in few-shot cross-domain settings rather than tautological reductions. This matches the default case of a self-contained construction with no load-bearing circular steps.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only abstract available; no free parameters, axioms, or invented entities are specified in the provided text.

pith-pipeline@v0.9.0 · 5730 in / 983 out tokens · 39109 ms · 2026-05-20T20:10:39.617939+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

structure-aware expert routing ... r_i^l = exp(s_i^{+l}/τ) / (exp(s_i^{+l}/τ) + exp(s_i^{-l}/τ)) ... load counter m_i ... prompt-based semantic fusion
IndisputableMonolith/Foundation/RealityFromDistinction.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

structure-conditioned experts ... pre-training on source-domain meta-path views

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.