Author name cluster

Yuankai Luo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

ICLR Conference 2025 Conference Paper

Beyond Random Masking: When Dropout meets Graph Convolutional Networks

Yuankai Luo
Xiao-Ming Wu 0003
Hao Zhu

Graph Convolutional Networks (GCNs) have emerged as powerful tools for learning on graph-structured data, yet the behavior of dropout in these models remains poorly understood. This paper presents a comprehensive theoretical analysis of dropout in GCNs, revealing that its primary role differs fundamentally from standard neural networks - preventing oversmoothing rather than co-adaptation. We demonstrate that dropout in GCNs creates dimension-specific stochastic sub-graphs, leading to a form of structural regularization not present in standard neural networks. Our analysis shows that dropout effects are inherently degree-dependent, resulting in adaptive regularization that considers the topological importance of nodes. We provide new insights into dropout's role in mitigating oversmoothing and derive novel generalization bounds that account for graph-specific dropout effects. Furthermore, we analyze the synergistic interaction between dropout and batch normalization in GCNs, uncovering a mechanism that enhances overall regularization. Our theoretical findings are validated through extensive experiments on both node-level and graph-level tasks across 14 datasets. Notably, GCN with dropout and batch normalization outperforms state-of-the-art methods on several benchmarks, demonstrating the practical impact of our theoretical insights.

Details

ICML Conference 2025 Conference Paper

Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence

Yuankai Luo
Lei Shi 0002
Xiao-Ming Wu 0003

Message-passing Graph Neural Networks (GNNs) are often criticized for their limited expressiveness, issues like over-smoothing and over-squashing, and challenges in capturing long-range dependencies. Conversely, Graph Transformers (GTs) are regarded as superior due to their employment of global attention mechanisms, which potentially mitigate these challenges. Literature frequently suggests that GTs outperform GNNs in graph-level tasks, especially for graph classification and regression on small molecular graphs. In this study, we explore the untapped potential of GNNs through an enhanced framework, GNN+, which integrates six widely used techniques: edge feature integration, normalization, dropout, residual connections, feed-forward networks, and positional encoding, to effectively tackle graph-level tasks. We conduct a systematic re-evaluation of three classic GNNs—GCN, GIN, and GatedGCN—enhanced by the GNN+ framework across 14 well-known graph-level datasets. Our results reveal that, contrary to prevailing beliefs, these classic GNNs consistently match or surpass the performance of GTs, securing top-three rankings across all datasets and achieving first place in eight. Furthermore, they demonstrate greater efficiency, running several times faster than GTs on many datasets. This highlights the potential of simple GNN architectures, challenging the notion that complex mechanisms in GTs are essential for superior graph-level performance. Our source code is available at https: //github. com/LUOyk1999/GNNPlus.

Details

ICLR Conference 2025 Conference Paper

Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning

Yuankai Luo
Hongkang Li
Qijiong Liu
Lei Shi 0002
Xiao-Ming Wu 0003

We present a novel end-to-end framework that generates highly compact (typically 6-15 dimensions), discrete (int4 type), and interpretable node representations—termed node identifiers (node IDs)—to tackle inference challenges on large-scale graphs. By employing vector quantization, we compress continuous node embeddings from multiple layers of a Graph Neural Network (GNN) into discrete codes, applicable under both self-supervised and supervised learning paradigms. These node IDs capture high-level abstractions of graph data and offer interpretability that traditional GNN embeddings lack. Extensive experiments on 34 datasets, encompassing node classification, graph classification, link prediction, and attributed graph clustering tasks, demonstrate that the generated node IDs significantly enhance speed and memory efficiency while achieving competitive performance compared to current state-of-the-art methods. Our source code is available at https://github.com/LUOyk1999/NodeID.

Details

NeurIPS Conference 2024 Conference Paper

Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification

Yuankai Luo
Lei Shi
Xiao-ming Wu

Graph Transformers (GTs) have recently emerged as popular alternatives to traditional message-passing Graph Neural Networks (GNNs), due to their theoretically superior expressiveness and impressive performance reported on standard node classification benchmarks, often significantly outperforming GNNs. In this paper, we conduct a thorough empirical analysis to reevaluate the performance of three classic GNN models (GCN, GAT, and GraphSAGE) against GTs. Our findings suggest that the previously reported superiority of GTs may have been overstated due to suboptimal hyperparameter configurations in GNNs. Remarkably, with slight hyperparameter tuning, these classic GNN models achieve state-of-the-art performance, matching or even exceeding that of recent GTs across 17 out of the 18 diverse datasets examined. Additionally, we conduct detailed ablation studies to investigate the influence of various GNN configurations—such as normalization, dropout, residual connections, and network depth—on node classification performance. Our study aims to promote a higher standard of empirical rigor in the field of graph machine learning, encouraging more accurate comparisons and evaluations of model capabilities. Our implementation is available at https: //github. com/LUOyk1999/tunedGNN.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Enhancing Graph Transformers with Hierarchical Distance Structural Encoding

Yuankai Luo
Hongkang Li
Lei Shi
Xiao-ming Wu

Graph transformers need strong inductive biases to derive meaningful attention scores. Yet, current methods often fall short in capturing longer ranges, hierarchical structures, or community structures, which are common in various graphs such as molecules, social networks, and citation networks. This paper presents a Hierarchical Distance Structural Encoding (HDSE) method to model node distances in a graph, focusing on its multi-level, hierarchical nature. We introduce a novel framework to seamlessly integrate HDSE into the attention mechanism of existing graph transformers, allowing for simultaneous application with other positional encodings. To apply graph transformers with HDSE to large-scale graphs, we further propose a high-level HDSE that effectively biases the linear transformers towards graph hierarchies. We theoretically prove the superiority of HDSE in terms of expressivity and generalization. Empirically, we demonstrate that graph transformers with HDSE excel in graph classification, regression on 7 graph-level datasets, and node classification on 11 large-scale graphs.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Improving Self-supervised Molecular Representation Learning using Persistent Homology

Yuankai Luo
Lei Shi
Veronika Thost

Self-supervised learning (SSL) has great potential for molecular representation learning given the complexity of molecular graphs, the large amounts of unlabelled data available, the considerable cost of obtaining labels experimentally, and the hence often only small training datasets. The importance of the topic is reflected in the variety of paradigms and architectures that have been investigated recently, most focus on designing views for contrastive learning. In this paper, we study SSL based on persistent homology (PH), a mathematical tool for modeling topological features of data that persist across multiple scales. It has several unique features which particularly suit SSL, naturally offering: different views of the data, stability in terms of distance preservation, and the opportunity to flexibly incorporate domain knowledge. We (1) investigate an autoencoder, which shows the general representational power of PH, and (2) propose a contrastive loss that complements existing approaches. We rigorously evaluate our approach for molecular property prediction and demonstrate its particular features in improving the embedding space: after SSL, the representations are better and offer considerably more predictive power than the baselines over different probing tasks; our loss increases baseline performance, sometimes largely; and we often obtain substantial improvements over very small datasets, a common scenario in practice.

PDF Details

TIST Journal 2023 Journal Article

Mobility Inference on Long-Tailed Sparse Trajectory

Lei Shi
Yuankai Luo
Shuai Ma
Hanghang Tong
Zhetao Li
Xiatian Zhang
Zhiguang Shan

Analyzing the urban trajectory in cities has become an important topic in data mining. How can we model the human mobility consisting of stay and travel states from the raw trajectory data? How can we infer these mobility states from a single user’s trajectory information? How can we further generalize the mobility inference to the real-world trajectory data that span multiple users and are sparsely sampled over time? In this article, based on formal and rigid definitions of the stay/travel mobility, we propose a single trajectory inference algorithm that utilizes a generic long-tailed sparsity pattern in the large-scale trajectory data. The algorithm guarantees a 100% precision in the stay/travel inference with a provable lower bound in the recall metric. Furthermore, we design a transformer-like deep learning architecture on the problem of mobility inference from multiple sparse trajectories. Several adaptations from the standard transformer network structure are introduced, including the singleton design to avoid the negative effect of sparse labels in the decoder side, the customized space-time embedding on features of location records, and the mask apparatus at the output side for loss function correction. Evaluations on three trajectory datasets of 40 million urban users validate the performance guarantees of the proposed inference algorithm and demonstrate the superiority of our deep learning model, in comparison to sequence learning methods in the literature. On extremely sparse trajectories, the deep learning model improves from the single trajectory inference algorithm with more than two times of overall and F1 accuracy. The model also generalizes to large-scale trajectory data from different sources with good scalability.

Details DOI

NeurIPS Conference 2023 Conference Paper

Transformers over Directed Acyclic Graphs

Yuankai Luo
Veronika Thost
Lei Shi

Transformer models have recently gained popularity in graph representation learning as they have the potential to learn complex relationships beyond the ones captured by regular graph neural networks. The main research question is how to inject the structural bias of graphs into the transformer architecture, and several proposals have been made for undirected molecular graphs and, recently, also for larger network graphs. In this paper, we study transformers over directed acyclic graphs (DAGs) and propose architecture adaptations tailored to DAGs: (1) An attention mechanism that is considerably more efficient than the regular quadratic complexity of transformers and at the same time faithfully captures the DAG structure, and (2) a positional encoding of the DAG's partial order, complementing the former. We rigorously evaluate our approach over various types of tasks, ranging from classifying source code graphs to nodes in citation networks, and show that it is effective in two important aspects: in making graph transformers generally outperform graph neural networks tailored to DAGs and in improving SOTA graph transformer performance in terms of both quality and efficiency.

PDF Details