Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization

• URL: http://arxiv.org/abs/2506.14114v1
• Date: Tue, 17 Jun 2025 02:12:19 GMT
• Title: Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization
• Authors: Khushnood Abbas, Ruizhe Hou, Zhou Wengang, Dong Shi, Niu Ling, Satyaki Nan, Alireza Abbasi,
• Abstract summary: The study looked at both inductive and transductive settings.<n>We meticulously analyzed the top ten model-loss combinations for each metric based on their average rank.<n>The GIN architecture always showed the highest-level average performance, especially with Cross-Entropy loss.
• Score: 1.2522462543913029
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph Neural Networks (GNNs) became useful for learning on non-Euclidean data. However, their best performance depends on choosing the right model architecture and the training objective, also called the loss function. Researchers have studied these parts separately, but a large-scale evaluation has not looked at how GNN models and many loss functions work together across different tasks. To fix this, we ran a thorough study - it included seven well-known GNN architectures. We also used a large group of 30 single plus mixed loss functions. The study looked at both inductive and transductive settings. Our evaluation spanned three distinct real-world datasets, assessing performance in both inductive and transductive settings using 21 comprehensive evaluation metrics. From these extensive results (detailed in supplementary information 1 \& 2), we meticulously analyzed the top ten model-loss combinations for each metric based on their average rank. Our findings reveal that, especially for the inductive case: 1) Hybrid loss functions generally yield superior and more robust performance compared to single loss functions, indicating the benefit of multi-objective optimization. 2) The GIN architecture always showed the highest-level average performance, especially with Cross-Entropy loss. 3) Although some combinations had overall lower average ranks, models such as GAT, particularly with certain hybrid losses, demonstrated incredible specialized strengths, maximizing the most top-1 results among the individual metrics, emphasizing subtle strengths for particular task demands. 4) On the other hand, the MPNN architecture typically lagged behind the scenarios it was tested against.

Related papers

• Loss Functions for Predictor-based Neural Architecture Search [6.014777261874645]
  We conduct the first comprehensive study on loss functions in performance predictors, categorizing them into three main types: regression, ranking, and weighted loss functions.<n>Our results reveal that specific categories of loss functions can be effectively combined to enhance predictor-based NAS.
  arXiv  Detail & Related papers  (2025-06-06T08:36:46Z)
• Next Generation Loss Function for Image Classification [0.0]
  We experimentally challenge the well-known loss functions, including cross entropy (CE) loss, by utilizing the genetic programming (GP) approach. One function, denoted as Next Generation Loss (NGL), clearly stood out showing same or better performance for all tested datasets.
  arXiv  Detail & Related papers  (2024-04-19T15:26:36Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• Global Minima, Recoverability Thresholds, and Higher-Order Structure in GNNS [0.0]
  We analyze the performance of graph neural network (GNN) architectures from the perspective of random graph theory. We show how both specific higher-order structures in synthetic data and the mix of empirical structures in real data have dramatic effects on GNN performance.
  arXiv  Detail & Related papers  (2023-10-11T17:16:33Z)
• Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons [50.33260238739837]
  Graph networks (GNNs) have demonstrated remarkable capabilities in learning from graph-structured data.<n>There remains a lack of analysis comparing GNNs and generalizations from an optimization and generalization perspective.
  arXiv  Detail & Related papers  (2023-06-24T10:21:11Z)
• Class Anchor Margin Loss for Content-Based Image Retrieval [97.81742911657497]
  We propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimize for the L2 metric without the need of generating pairs. We evaluate the proposed objective in the context of few-shot and full-set training on the CBIR task, by using both convolutional and transformer architectures.
  arXiv  Detail & Related papers  (2023-06-01T12:53:10Z)
• Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks [52.566735716983956]
  We propose a graph gradual pruning framework termed CGP to dynamically prune GNNs. Unlike LTH-based methods, the proposed CGP approach requires no re-training, which significantly reduces the computation costs. Our proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of existing methods.
  arXiv  Detail & Related papers  (2022-07-18T14:23:31Z)
• Benchmarking Deep AUROC Optimization: Loss Functions and Algorithmic Choices [37.559461866831754]
  We benchmark a variety of loss functions with different algorithmic choices for deep AUROC optimization problem. We highlight the essential choices such as positive sampling rate, regularization, normalization/activation, and weights. Our findings show that although Adam-type method is more competitive from training perspective, but it does not outperform others from testing perspective.
  arXiv  Detail & Related papers  (2022-03-27T00:47:00Z)
• Tackling Oversmoothing of GNNs with Contrastive Learning [35.88575306925201]
  Graph neural networks (GNNs) integrate the comprehensive relation of graph data and representation learning capability. Oversmoothing makes the final representations of nodes indiscriminative, thus deteriorating the node classification and link prediction performance. We propose the Topology-guided Graph Contrastive Layer, named TGCL, which is the first de-oversmoothing method maintaining all three mentioned metrics.
  arXiv  Detail & Related papers  (2021-10-26T15:56:16Z)
• Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning [63.97983530843762]
  Graph Neural Networks (GNNs) have achieved great success in graph representation learning. GNNs generate identical representations for graph substructures that may in fact be very different. More powerful GNNs, proposed recently by mimicking higher-order tests, are inefficient as they cannot sparsity of underlying graph structure. We propose Distance Depiction (DE) as a new class of graph representation learning.
  arXiv  Detail & Related papers  (2020-08-31T23:15:40Z)
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks [105.14867349802898]
  Graph Convolutional Network (GCN) stacks several layers and in each layer performs a PROPagation operation (PROP) and a TRANsformation operation (TRAN) for learning node representations over graph-structured data. GCNs tend to suffer performance drop when the model gets deep. We study performance degradation of GCNs by experimentally examining how stacking only TRANs or PROPs works.
  arXiv  Detail & Related papers  (2020-06-12T12:12:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.