Graph Your Own Prompt

Xi Ding; Lei Wang; Piotr Koniusz; Yongsheng Gao

cs.LGSep 27, 2025

Graph Your Own Prompt

Authors: Xi Ding, Lei Wang, Piotr Koniusz, Yongsheng Gao

Organizations: Griffith University · Australian National University · Data61/CSIRO · University of New South Wales

Abstract

We propose Graph Consistency Regularization (GCR), a novel framework that injects relational graph structures, derived from model predictions, into the learning process to promote class-aware, semantically meaningful feature representations. Functioning as a form of self-prompting, GCR enables the model to refine its internal structure using its own outputs. While deep networks learn rich representations, these often capture noisy inter-class similarities that contradict the model's predicted semantics. GCR addresses this issue by introducing parameter-free Graph Consistency Layers (GCLs) at arbitrary depths. Each GCL builds a batch-level feature similarity graph and aligns it with a global, class-aware masked prediction graph, derived by modulating softmax prediction similarities with intra-class indicators. This alignment enforces that feature-level relationships reflect class-consistent prediction behavior, acting as a semantic regularizer throughout the network. Unlike prior work, GCR introduces a multi-layer, cross-space graph alignment mechanism with adaptive weighting, where layer importance is learned from graph discrepancy magnitudes. This allows the model to prioritize semantically reliable layers and suppress noisy ones, enhancing feature quality without modifying the architecture or training procedure. GCR is model-agnostic, lightweight, and improves semantic structure across various networks and datasets. Experiments show that GCR promotes cleaner feature structure, stronger intra-class cohesion, and improved generalization, offering a new perspective on learning from prediction structure. Project website Code

Figures & tables

Panel of Figure 1 — Figure 1 : Relational graph visualization using a batch of 64 samples from CIFAR-10 on (left) DenseNet-121 and (right) MobileNet. We compare the baselines with their counterparts augmented by our GCLs. Our method promotes richer, class-aware semantic representations by acting as a form of self-prompting . For DenseNet-121, the baseline feature relational graph tends to connect samples based on superficial visual similarity ( e.g . , deer, horse, and automobile), often ignoring semantic boundaries. In contrast, our GCL-enhanced model produces more semantically coherent groupings , clearly separating animals from vehicles. On MobileNet, the prediction relational graph further highlights the strength of our method, demonstrating cleaner, more distinct class relationships compared to the baseline. These improvements reflect the effectiveness of our model in aligning feature and prediction spaces with semantic structure, despite being lightweight and parameter-free .

Figure 2 : Our parameter-free Graph Consistency Layer (GCL), highlighted in red, can be inserted after any micro-network block ( e.g . , Inception) or specific layer ( e.g . , fully connected). Each GCL constructs a relational graph from batch-level features using a similarity metric ( e.g . , cosine). A reference graph is generated from softmax predictions and masked by intra-class indicators: binary masks identifying semantically consistent pairs. Each GCL enforces alignment between masked prediction graph and the feature-level graphs. The resulting consistency signals are adaptively weighted, forming the Graph Consistency Regularization (GCR) framework, which integrates with the primary loss ( e.g . , cross-entropy), acting as a semantic regularizer to guide learning.

Panel of Figure 3 — Figure 3 : Feature map visualizations from models trained on identical data batches : (top) baseline and (bottom) our GCL-augmented model. Brighter red regions indicate stronger feature activations. Compared to the baseline, GCL-enhanced maps more clearly emphasize class-discriminative cues, e.g . , cat faces, ears, and eyes, and for dogs, tongues, noses, and facial contours, reflecting improved focus and interpretability. GCL also yields higher classification accuracy (98.1% $\rightarrow$ 99.8%).

Panel of Figure 4 — Figure 4 : Relational graph visualization on Kaggle cats vs . dogs. We compare the best baseline model and our GCL-augmented model using the same batch of 32 samples (red = cat, blue = dog). The baseline consists of four convolutional blocks and two fully connected layers; our method inserts a Graph Consistency Layer (GCL) after each, totaling six GCLs. The top row shows the baseline (without GCLs); the bottom row shows our GCL-enhanced model. Each column visualizes the relational graph at a specific layer, from early features (left) to final predictions (right). Early layers exhibit weak connectivity, as low-level features poorly capture class semantics. As depth increases, both models shift toward more structured, class-separable relationships. GCLs amplify this effect by attenuating low-similarity inter-class edges and reinforcing intra-class coherence, leading to improved accuracy (98.1% vs . 99.8%). For clarity, edges with similarity $<$ 0.4 are omitted.

	MAE	MNet	SN	SQNet	GLNet	Rx-50	Rx-101	R34	R50	R101	D121	Mean
Baseline	88.95 ±0.33	90.23 ±0.25	91.21 ±0.28	92.30 ±0.25	94.10 ±0.26	94.57 ±0.29	95.12 ±0.30	94.83 ±0.25	95.03 ±0.28	95.22 ±0.31	95.01 ±0.27	93.32 ±2.26
Early GCL	89.42 ±0.25	91.17 ±0.22	92.33 ±0.33	92.59 ±0.21	94.89 ±0.23	95.48 ±0.22	95.63 ±0.25	95.55 ±0.18	95.57 ±0.23	95.39 ±0.26	95.81 ±0.17	93.98 ±2.22
Mid GCL	89.77 ±0.22	91.15 ±0.18	92.58 ±0.19	92.40 ±0.20	94.82 ±0.21	95.47 ±0.19	95.39 ±0.24	95.69 ±0.23	95.61 ±0.20	95.75 ±0.17	95.51 ±0.22	94.01 ±2.15
Late GCL	89.70 ±0.29	91.40 ±0.19	92.36 ±0.21	92.80 ±0.19	94.88 ±0.19	95.35 ±0.28	95.71 ±0.26	95.69 ±0.19	95.66 ±0.17	95.51 ±0.24	95.72 ±0.22	94.07 ±2.14
Early+Mid	89.52 ±0.19	90.77 ±0.26	92.56 ±0.21	92.27 ±0.25	94.79 ±0.18	95.33 ±0.27	95.55 ±0.23	95.46 ±0.20	95.51 ±0.21	95.37 ±0.19	95.64 ±0.20	93.89 ±2.22
Mid+Late	89.59 ±0.28	91.23 ±0.20	92.79 ±0.20	92.86 ±0.23	94.61 ±0.22	95.51 ±0.19	95.38 ±0.27	95.45 ±0.18	95.33 ±0.26	95.52 ±0.14	95.70 ±0.19	94.00 ±2.09

Table 1 : Accuracy (%) on CIFAR-10 across models. Results are shown for MobileNet (MNet), ShuffleNet (SN), SqueezeNet (SQNet), GoogLeNet (GLNet), ResNeXt-50/101 (Rx-50/101), ResNet-34/50/101 (R34/R50/R101), DenseNet-121 (D121), and MAE under various GCL configurations (Early, Mid, Late, combinations, Full). Bold indicates the best improvements over baselines; underlines mark the second-best. The final column shows the average accuracy for each configuration.

	MAE	MNet	SN	SQNet	Rx-50	Rx-101	R34	R50	D121	Mean
Baseline	64.29 ±0.34	65.95 ±0.25	70.11 ±0.30	69.43 ±0.27	77.75 ±0.29	77.83 ±0.30	76.82 ±0.28	77.31 ±0.29	77.09 ±0.27	72.95 ±5.50
Early GCL	65.05 ±0.29	67.45 ±0.21	71.96 ±0.27	70.90 ±0.20	79.18 ±0.22	79.69 ±0.27	77.90 ±0.22	79.37 ±0.25	79.41 ±0.22	74.55 ±5.78
Mid GCL	64.99 ±0.30	67.88 ±0.21	71.89 ±0.24	70.21 ±0.25	79.07 ±0.19	79.28 ±0.26	77.83 ±0.20	78.90 ±0.24	79.26 ±0.21	74.37 ±5.66
Late GCL	65.54 ±0.27	68.32 ±0.20	71.42 ±0.24	70.55 ±0.22	79.54 ±0.20	79.83 ±0.21	78.31 ±0.20	79.42 ±0.21	79.69 ±0.23	74.74 ±5.73
Early+Mid	65.23 ±0.31	67.62 ±0.24	71.50 ±0.28	70.47 ±0.19	78.90 ±0.18	79.25 ±0.20	77.41 ±0.19	78.58 ±0.24	79.22 ±0.20	74.28 ±5.56
Mid+Late	65.27 ±0.28	68.33 ±0.19	71.63 ±0.28	70.30 ±0.22	78.91 ±0.17	79.57 ±0.21	77.30 ±0.20	78.85 ±0.22	79.54 ±0.24	74.41 ±5.55

Table 2 : Accuracy (%) on CIFAR-100 across models.

Panel of Figure 5 — Figure 5 : Relational graph comparison across five models on the same batch. Top row: baselines; bottom row: GCL-augmented versions, showing sparser inter-class connections and stronger class-aware structure , highlighting GCL’s effectiveness in enhancing relational representations.

	ViT ${}_{\text{/32}}$	ViT ${}_{\text{/16}}$	CeiT	MViT ${}_{\text{XXS}}$	MViT ${}_{\text{XS}}$	MViT	Swin	MNet	R18SD	SER18	R34	Mean
Baseline	37.79 ±0.35	40.05 ±0.33	49.95 ±0.29	49.28 ±0.29	51.58 ±0.27	52.68 ±0.27	54.27 ±0.25	57.81 ±0.25	63.49 ±0.26	65.65 ±0.24	67.51 ±0.25	53.64 ±9.62
Early GCL	39.02 ±0.29	40.98 ±0.19	51.22 ±0.20	50.11 ±0.28	51.33 ±0.26	53.91 ±0.22	54.88 ±0.25	57.93 ±0.21	63.81 ±0.19	66.52 ±0.22	67.79 ±0.19	54.32 ±9.39
Mid GCL	38.61 ±0.23	40.95 ±0.19	50.30 ±0.19	49.92 ±0.26	51.43 ±0.22	53.88 ±0.20	55.23 ±0.24	57.63 ±0.20	64.03 ±0.22	65.66 ±0.23	67.62 ±0.20	54.11 ±9.38
Late GCL	37.98 ±0.28	40.35 ±0.25	50.82 ±0.20	49.77 ±0.21	51.99 ±0.23	54.10 ±0.19	55.47 ±0.21	57.87 ±0.23	63.79 ±0.19	65.85 ±0.25	67.61 ±0.19	54.18 ±9.56
Early+Mid	39.08 ±0.25	41.26 ±0.18	50.25 ±0.25	49.73 ±0.22	51.57 ±0.19	53.91 ±0.23	54.95 ±0.19	57.49 ±0.19	64.18 ±0.20	65.86 ±0.24	67.74 ±0.23	54.18 ±9.32
Mid+Late	38.44 ±0.18	40.52 ±0.28	50.09 ±0.25	50.55 ±0.18	51.48 ±0.21	53.90 ±0.20	55.62 ±0.23	57.65 ±0.21	64.29 ±0.17	65.95 ±0.19	67.58 ±0.21	54.19 ±9.52

Table 3 : Accuracy (%) on Tiny ImageNet across models. All results are obtained by training models from scratch. We also evaluate Stochastic ResNet-18 (R18SD) and SE-ResNet-18 (SER18).

Panel of Figure 6 — Figure 6 : Performance gains ( $\Delta$ ,%) from adding GCLs with different configurations across various weighting schemes. Darker red indicates larger gains. Adaptive weighting achieves the highest improvement, showing the value of graph misalignment as a guidance signal. (c) and (d) show that GCL-augmented ShuffleNet yields more compact intra-class clusters and better inter-class separation.

Method	iFormer-S	iFormer-B	ViT-B/16	ViG-B
Baseline	83.4 ±0.40	84.6 ±0.45	74.3 ±0.51	82.3 ±0.42
Early GCL	83.8 ±0.31	85.0 ±0.40	74.7 ±0.44	82.8 ±0.35
Mid GCL	83.8 ±0.39	85.5 ±0.33	75.2 ±0.36	83.0 ±0.34
Late GCL	84.5 ±0.29	86.1 ±0.30	75.8 ±0.33	84.0 ±0.30
Early + Mid	84.3 ±0.33	85.9 ±0.38	75.6 ±0.41	83.7 ±0.33
Mid + Late	84.8 ±0.28	85.9 ±0.37	75.6 ±0.34	83.9 ±0.30

Table 4 : Comparison of iFormer, ViT, and ViG with different GCL integration strategies on ImageNet-1K. Results are averaged over three runs.

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 7 — Figure 7 : t-SNE visualizations of feature representations on CIFAR-10. (Left) Original model architectures; (Right) corresponding GCL-augmented models. Our method consistently enhances feature structure across diverse architectures, including MobileNet, ResNet-34, and MAE (with ViT-Tiny encoder), by yielding tighter intra-class clusters and improved inter-class separation. Notably, GCR distinctly separates semantic groups such as animals and vehicles ( e.g . , (e) vs . (f)). Importantly, GCL is lightweight and introduces no additional parameters.

Figure 8 : Effect of batch size (

n

) in the GCR framework. We evaluate using the Masked Autoencoder model. The top row shows the baseline; the bottom row shows the GCL-augmented counterpart. From left to right, the relational graphs are constructed on softmax predictions as

n

increases from 16 to 128. As batch size grows, GCL-augmented models consistently exhibit tighter intra-class clusters and clearer inter-class separation.

ShuffleNet on CIFAR-10			CeiT on Tiny ImageNet
Batch Size	+ GCR	Baseline	Batch Size	+ GCR	Baseline
16	79.90 $\pm$ 0.38	78.88 $\pm$ 0.41	16	44.84 $\pm$ 0.31	43.78 $\pm$ 0.35
32	87.91 $\pm$ 0.36	86.91 $\pm$ 0.37	32	47.55 $\pm$ 0.29	46.89 $\pm$ 0.31
64	91.26 $\pm$ 0.25	90.64 $\pm$ 0.35	64	49.19 $\pm$ 0.25	48.09 $\pm$ 0.30
128	92.79 $\pm$ 0.20	91.21 $\pm$ 0.28	128	51.22 $\pm$ 0.20	49.95 $\pm$ 0.29
256	92.89 $\pm$ 0.25	92.07 $\pm$ 0.27	256	50.77 $\pm$ 0.19	49.62 $\pm$ 0.24

Appendix

Table 5 : Effect of batch size on GCR performance for ShuffleNet (CIFAR-10) and CeiT (Tiny ImageNet).

Method	Cosine	RBF	Polynomial	Sigmoid	Laplacian
Baseline	65.95 $\pm$ 0.25	65.95 $\pm$ 0.25	65.95 $\pm$ 0.25	65.95 $\pm$ 0.25	65.95 $\pm$ 0.25
Early GCL	67.53 $\pm$ 0.21	66.66 $\pm$ 0.28	66.59 $\pm$ 0.29	66.63 $\pm$ 0.30	66.42 $\pm$ 0.28
Mid GCL	67.91 $\pm$ 0.19	67.04 $\pm$ 0.24	66.97 $\pm$ 0.24	67.01 $\pm$ 0.36	66.80 $\pm$ 0.29
Late GCL	68.32 $\pm$ 0.20	67.45 $\pm$ 0.23	67.38 $\pm$ 0.29	67.42 $\pm$ 0.29	67.21 $\pm$ 0.31
Early + Mid	67.62 $\pm$ 0.23	66.75 $\pm$ 0.24	66.68 $\pm$ 0.21	66.72 $\pm$ 0.27	66.51 $\pm$ 0.29
Mid + Late	68.26 $\pm$ 0.18	67.39 $\pm$ 0.23	67.32 $\pm$ 0.23	67.36 $\pm$ 0.31	67.15 $\pm$ 0.27

Appendix

Table 6 : Performance comparison of different GCL integration strategies with various kernels.

Model	Silhouette		SepRatio		Confidence
Model	Baseline	+ GCR	Baseline	+ GCR	Baseline	+ GCR
DenseNet-121	0.4724	0.5001	2.2278	2.3325	0.9746	0.9805
ShuffleNet	0.2806	0.4083	1.7692	2.0472	0.9568	0.9619
SqueezeNet	-0.1245	-0.0825	1.0008	1.0494	0.9603	0.9660
ResNet-34	0.6032	0.7314	3.1015	4.4144	0.9801	0.9870
ResNet-50	0.5314	0.6186	2.5480	3.2294	0.9789	0.9835

Appendix

Table 7 : Quantitative metrics showing improvements in feature clustering and confidence with GCR.

	plane	auto	bird	cat	deer	dog	frog	horse	ship	truck
plane	0.93	0.01	0.02	0.01					0.03	0.01
auto	0.01	0.96								0.03
bird	0.02		0.88	0.03	0.02	0.01	0.02	0.01
cat	0.01		0.02	0.83	0.02	0.08			0.01	0.01
deer	0.01		0.01	0.02	0.93	0.01	0.01	0.01
dog			0.01	0.09	0.02	0.86		0.01

Appendix

Table 8 : CIFAR-10 confusion matrix for the baseline model.

	plane	auto	bird	cat	deer	dog	frog	horse	ship	truck
plane	0.94		0.02	0.01					0.01	0.01
auto		0.97								0.02
bird	0.01		0.89	0.03	0.02	0.02	0.01	0.01
cat	0.01		0.01	0.85	0.01	0.08		0.01	0.01	0.01
deer	0.01		0.01	0.02	0.94	0.01	0.01	0.01
dog			0.01	0.07	0.01	0.88		0.01

Appendix

Table 9 : CIFAR-10 confusion matrix for the model with GCR .

Model	Pre-freeze	Post-freeze	Performance Drop
Model A (Early-GCR)	66.8%	66.1%	0.7%
Model B (Late-GCR)	66.4%	65.1%	1.2%

Appendix

Table 10 : Impact of early vs . late GCR on feature robustness in ShuffleNet. Pre-freeze and post-freeze top-1 accuracy are reported, along with the performance drop.

Method	CIFAR-10	CIFAR-100	ImageNet-1K
ResNet-18
CNN2GNN [ 101 ]	95.51 $\pm$ 0.42	74.80 $\pm$ 0.81	60.12 $\pm$ 1.02
CNN2GNN + GCR	95.87 $\pm$ 0.31	76.23 $\pm$ 0.38	62.47 $\pm$ 0.47
CNN2Transformer [ 101 ]	95.79 $\pm$ 0.24	77.39 $\pm$ 0.20	71.12 $\pm$ 0.35
CNN2Transformer + GCR	95.96 $\pm$ 0.35	78.23 $\pm$ 0.30	72.33 $\pm$ 0.31
ResNet-34

Appendix

Table 11 : Performance comparison on CIFAR-10, CIFAR-100, and ImageNet-1K.

Model	ViG-Ti [ 37 ]	ViG-Ti + GCR	ViG-S [ 37 ]	ViG-S + GCR	ViG-B [ 37 ]	ViG-B + GCR
Accuracy	73.9	74.9	80.4	81.7	82.3	84.0

Appendix

Table 12 : Results on ImageNet-1K.

	MobileNet	ShuffleNet	SqueezeNet
Baseline	65.95 $\pm$ 0.25	70.11 $\pm$ 0.30	69.43 $\pm$ 0.27
GCR (one-hot labels)	67.35 $\pm$ 0.24	71.28 $\pm$ 0.26	70.49 $\pm$ 0.25
GCR (soft predictions, ours )	68.32 $\pm$ 0.20	71.96 $\pm$ 0.27	71.03 $\pm$ 0.24

Appendix

Table 13 : Comparison of GCR with one-hot labels vs . soft predictions on CIFAR-100 (average over 10 runs).

$\lambda$	0	0.1	0.3	0.5	0.7	1	3	5	7	10
Top-1 Acc (%)	76.76	76.80	76.87	77.32	77.61	78.38	76.74	76.02	75.90	75.37

Appendix

Table 14 : Impact of bottleneck strength

\lambda

on CIFAR-100 (ResNet-34).

$\tau$	$0$	$1\mathrm{e}{-5}$	$1\mathrm{e}{-4}$	$1\mathrm{e}{-3}$	$1\mathrm{e}{-2}$
Accuracy	78.38	78.32	78.27	78.13	76.04

Appendix

Table 15 : Effect of varying

\tau

on CIFAR-100 with ResNet-34.

$\tau$ (deg)	Acc	1st		2nd		3rd		4th		5th		6th
$\tau$ (deg)	Acc	intra	inter	intra	inter	intra	inter	intra	inter	intra	inter	intra	inter
baseline	65.95	38.71	13.81	22.30	7.56	12.00	5.27	5.10	4.24	17.71	19.49	8.64	9.69
ours (0.00)	68.14	31.21	12.02	18.18	7.61	9.98	4.28	3.94	3.25	16.82	18.69	8.30	9.32
0.08	68.21	31.25	12.56	18.28	6.54	9.92	4.46	4.10	3.28	18.77	19.52	9.23	9.74
0.26	67.68	36.28	13.11	20.93	7.15	10.94	4.92	4.58	3.81	17.72	19.08	8.72	9.50
0.81	67.37	35.39	13.72	20.44	6.92	11.02	4.89	4.70	3.89	17.74	18.87	8.70	9.41

Appendix

Table 16 : Results on CIFAR-100 (100 classes) with MobileNet. Accuracy and intra-/inter-class variance across six layers under different

\tau

$\tau$ (deg)	Acc	1st		2nd		3rd		4th		5th		6th
$\tau$ (deg)	Acc	intra	inter	intra	inter	intra	inter	intra	inter	intra	inter	intra	inter
baseline	77.46	30.30	8.86	17.94	4.30	9.25	2.97	3.01	2.46	9.09	12.27	4.45	6.12
ours (0.00)	77.54	30.36	8.65	17.95	4.43	9.34	2.99	3.22	2.56	9.69	12.57	4.73	6.27
0.08	77.72	31.59	9.22	18.24	4.42	9.57	3.08	3.33	2.61	9.91	12.56	4.87	6.27
0.26	77.36	32.04	9.80	18.67	4.58	9.57	3.07	3.28	2.70	9.85	12.69	4.83	6.33
0.81	77.69	31.36	9.59	18.17	4.38	9.50	3.04	3.15	2.60	9.70	12.63	4.77	6.30

Appendix

Table 17 : Results on CIFAR-100 (20 super-classes) with MobileNet. Accuracy and intra-/inter-class variance across six layers under different

\tau

Explore similar work

GCCM: Enhancing Generative Graph Prediction via Contrastive Consistency Model
May 7, 2026Shaozhen Ma, Wei Huang, Hanchen Wang +2Physics-Guided Diffusion Generative Models
University of New South Wales · University of Technology Sydney
Structure-Feature Aligned Graph Learning via Alternating Constrained Optimization
Jul 13, 2026Chengcheng Yan, Qingsong WangGraph Neural Networks Sparse Spatial Anchors
College of Artificial Intelligence, Shaoxing Institute of Technology, Shaoxing, 312000, China. · School of Mathematics and Computational Science, Xiangtan University, Xiangtan, 411105, China.
SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
Jul 1, 2026Yuting Zhang, Yanbei Liu, Zhitao Xiao +3Graph Representation Learning
School of Electronics and Information Engineering, Tiangong University, Tianjin, China · School of Life Sciences, Tiangong University, Tianjin, China · School of Electrical and Infomation Engineering, Tianjin University, Tianjin, China +1

May 7, 2026, cs.AIJ/K move · Enter open · S save

GCCM: Enhancing Generative Graph Prediction via Contrastive Consistency Model

Shaozhen Ma, Wei Huang, Hanchen Wang, Dong Wen+1

University of New South Wales · University of Technology Sydney

Physics-Guided Diffusion Generative Models Distribution Matching

Open paper AskPDF arXiv

Conditional generative models, particularly diffusion-based methods, have recently been applied to graph prediction by modeling the target as a conditional distribution given the input graph, yielding competitive results compared to deterministic predictor. However, existing diffusion-based prediction methods typically require expensive iterative denoising at inference and often suffer from unstable sampling, which motivates recent efforts to reduce inference denoising steps and enable stable sampling via techniques such as consistency training. Despite this progress, we find that existing consistency training methods for graph prediction could potentially fall into a shortcut solution: the model may attempt to satisfy the self-consistency constraint by ignoring the noisy target (i.e., assigning it negligible weight), ultimately collapsing into a purely deterministic predictor. To mitigate such shortcut solution, we propose GCCM, a graph contrastive consistency model that goes beyond isolated pairwise matching between the same target at different noise levels by introducing negative pairs into a contrastive consistency objective. This adds an additional separation requirement, making the shortcut solution no longer trivially sufficient to satisfy the proposed objective. Moreover, we apply feature perturbation to the input node/edge features to break identical conditioning on the input graph, so that the shortcut no longer yields the same predictions across noise levels and becomes less attractive. Extensive experiments on benchmark datasets demonstrate that GCCM mitigates the shortcut solution and yields consistent performance improvements in graph prediction compared to deterministic predictors.

Abstract

Explore similar work

GCCM: Enhancing Generative Graph Prediction via Contrastive Consistency Model

Structure-Feature Aligned Graph Learning via Alternating Constrained Optimization

SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport