arXiv subjects

Yilin Bi

Publications and source records attributed to Yilin Bi.

11 recordsLinked to original sources

arXiv2026

Rethinking Sampling Strategy in Link Prediction

Many real-world networks are incomplete, making link prediction a fundamental challenge in network science. To train parameters and evaluate algorithms, observed links are usually divided into three subsets, namely training, validation, and probe sets. This division implicitly involves two sampling processes: first-stage sampling yields the probe set and second-stage sampling obtains the variation set. To date, our understanding of how these two sampling processes affect algorithm performance remains quite limited. To address this issue, we propose a sampling scheme called $\beta$-sampling, where the sampling probability of a link is proportional to the product of the degrees of its two endpoints raised to the power of $\beta$. Experiments on 45 real-world networks reveal that the structural characteristics of missing links, as simulated via varying probe sets, substantially impact prediction accuracy. When missing links tend to connect high-degree nodes, such links can be predicted accurately with ease. Furthermore, even with a fixed probe set, second-stage sampling still exerts a significant influence on prediction accuracy. Notably, the optimal second-stage sampling strategy differs from \textit{random sampling} (which randomly selects links to form the validation set) and \textit{consistent sampling} (which guarantees that links in the validation and probe sets share identical structural characteristics).

cs.SI↗

arXiv2026

Hypergraph Mining via Proximity Matrix

Hypergraphs serve as an effective tool widely adopted to characterize higher-order interactions in complex systems. The most intuitive and commonly used mathematical instrument for representing a hypergraph is the incidence matrix, in which each entry is binary, indicating whether the corresponding node belongs to the corresponding hyperedge. Although the incidence matrix has become a foundational tool for hypergraph analysis and mining, we argue that its binary nature is insufficient to accurately capture the complexity of node-hyperedge relationships arising from the fact that different hyperedges can contain vastly different numbers of nodes. Accordingly, based on the resource allocation process on hypergraphs, we propose a continuous-valued matrix to quantify the proximity between nodes and hyperedges. To verify the effectiveness of the proposed proximity matrix, we investigate three important tasks in hypergraph mining: link prediction, vital nodes identification, and community detection. Experimental results on numerous real-world hypergraphs show that simply designed algorithms centered on the proximity matrix significantly outperform benchmark algorithms across these three tasks.

cs.SI↗

arXiv2025

Domain matters: Towards domain-informed evaluation for link prediction

Link prediction, a foundational task in complex network analysis, has extensive applications in critical scenarios such as social recommendation, drug target discovery, and knowledge graph completion. However, existing evaluations of algorithmic often rely on experiments conducted on a limited number of networks, assuming consistent performance rankings across domains. Despite the significant disparities in generative mechanisms and semantic contexts, previous studies often improperly highlight ``universally optimal" algorithms based solely on naive average over networks across domains. This paper systematically evaluates 12 mainstream link prediction algorithms across 740 real-world networks spanning seven domains. We present substantial empirical evidence elucidating the performance of algorithms in specific domains. This findings reveal a notably low degree of consistency in inter-domain algorithm rankings, a phenomenon that stands in stark contrast to the high degree of consistency observed within individual domains. Principal Component Analysis shows that response vectors formed by the rankings of the 12 algorithms cluster distinctly by domain in low-dimensional space, thus confirming domain attributes as a pivotal factor affecting algorithm performance. We propose a metric called Winner Score that could identify the superior algorithm in each domain: Non-Negative Matrix Factorization for social networks, Neighborhood Overlap-aware Graph Neural Networks for economics, Graph Convolutional Networks for chemistry, and L3-based Resource Allocation for biology. However, these domain-specific top-performing algorithms tend to exhibit suboptimal performance in other domains. This finding underscores the importance of aligning an algorithm's mechanism with the network structure.

stat.OT↗

arXiv2025

Impacts of Data Splitting Strategies on Parameterized Link Prediction Algorithms

Link prediction is a fundamental problem in network science, aiming to infer potential or missing links based on observed network structures. With the increasing adoption of parameterized models, the rigor of evaluation protocols has become critically important. However, a previously common practice of using the test set during hyperparameter tuning has led to human-induced information leakage, thereby inflating the reported model performance. To address this issue, this study introduces a novel evaluation metric, Loss Ratio, which quantitatively measures the extent of performance overestimation. We conduct large-scale experiments on 60 real-world networks across six domains. The results demonstrate that the information leakage leads to an average overestimation of about 3.6%, with the bias reaching over 15% for specific algorithms. Meanwhile, heuristic and random-walk-based methods exhibit greater robustness and stability. The analysis uncovers a pervasive information leakage issue in link prediction evaluation and underscores the necessity of adopting standardized data splitting strategies to enable fair and reproducible benchmarking of link prediction models.

stat.OT↗

arXiv2025

Predictability of Complex Systems

The study of complex systems has attracted widespread attention from researchers in the fields of natural sciences, social sciences, and engineering. Prediction is one of the central issues in this field. Although most related studies have focused on prediction methods, research on the predictability of complex systems has received increasing attention across disciplines--aiming to provide theories and tools to address a key question: What are the limits of prediction accuracy? Predictability itself can serve as an important feature for characterizing complex systems, and accurate estimation of predictability can provide a benchmark for the study of prediction algorithms. This allows researchers to clearly identify the gap between current prediction accuracy and theoretical limits, thereby helping them determine whether there is still significant room to improve existing algorithms. More importantly, investigating predictability often requires the development of new theories and methods, which can further inspire the design of more effective algorithms. Over the past few decades, this field has undergone significant evolution. In particular, the rapid development of data science has introduced a wealth of data-driven approaches for understanding and quantifying predictability. This review summarizes representative achievements, integrating both data-driven and mechanistic perspectives. After a brief introduction to the significance of the topic in focus, we will explore three core aspects: the predictability of time series, the predictability of network structures, and the predictability of dynamical processes. Finally, we will provide extensive application examples across various fields and outline open challenges for future research.

physics.soc-ph↗

arXiv2025

Performances and Correlations of Centrality Measures in Complex Networks

Numerous centrality measures have been proposed to evaluate the importance of nodes in networks, yet comparative analyses of these measures remain limited. Based on 80 real-world networks, we conducted an empirical analysis of 16 representative centrality measures. In general, there exists a moderate to high level of correlation between node rankings derived from different measures. We identified two distinct communities: one comprising 4 measures and the other 7 measures. Measures within the same community exhibit exceptionally strong pairwise correlations. In contrast, the remaining five measures display markedly different behaviors, showing weak correlations not only among themselves but also with the other measures. This suggests that each of these five measures likely captures unique properties of node importance. Further analysis reveals that the distribution patterns of the most influential nodes identified by different centrality measures vary significantly: some measures tend to cluster influential nodes closely together, while others disperse them across distant locations within the network. Using the epidemic spreading model, we found that LocalRank, Subgraph Centrality, and Katz Centrality perform best in identifying the most influential single node, whereas Leverage Centrality, Collective Influence, and Cycle Ratio excel in identifying the most influential node sets. Overall, measures that identify influential nodes with larger topological distances between them tend to perform better in detecting influential node sets. Interestingly, despite being applied to the same dynamical process, when using two seemingly similar tasks, identifying influential nodes versus identifying influential node sets, to rank the performances of the 16 centrality measures, the resulting rankings are negatively correlated.

stat.OT↗

arXiv2025

Hard negative sampling in hyperedge prediction

Hypergraph, which allows each hyperedge to encompass an arbitrary number of nodes, is a powerful tool for modeling multi-entity interactions. Hyperedge prediction is a fundamental task that aims to predict future hyperedges or identify existent but unobserved hyperedges based on those observed. In link prediction for simple graphs, most observed links are treated as positive samples, while all unobserved links are considered as negative samples. However, this full-sampling strategy is impractical for hyperedge prediction, due to the number of unobserved hyperedges in a hypergraph significantly exceeds the number of observed ones. Therefore, one has to utilize some negative sampling methods to generate negative samples, ensuring their quantity is comparable to that of positive samples. In current hyperedge prediction, randomly selecting negative samples is a routine practice. But through experimental analysis, we discover a critical limitation of random selecting that the generated negative samples are too easily distinguishable from positive samples. This leads to premature convergence of the model and reduces the accuracy of prediction. To overcome this issue, we propose a novel method to generate negative samples, named as hard negative sampling (HNS). Unlike traditional methods that construct negative hyperedges by selecting node sets from the original hypergraph, HNS directly synthesizes negative samples in the hyperedge embedding space, thereby generating more challenging and informative negative samples. Our results demonstrate that HNS significantly enhances both accuracy and robustness of the prediction. Moreover, as a plug-and-play technique, HNS can be easily applied in the training of various hyperedge prediction models based on representation learning.

cs.SI↗

arXiv2024

Beyond Pairwise Interactions: Unveiling the Role of Higher-Order Interactions via Stepwise Reduction

Complex systems, such as economic, social, biological, and ecological systems, usually feature interactions not only between pairwise entities but also among three or more entities. These multi-entity interactions are known as higher-order interactions. Hypergraph, as a mathematical tool, can effectively characterize higher-order interactions, where nodes denote entities and hyperedges represent interactions among multiple entities. Meanwhile, all higher-order interactions can also be projected into a number of lower-order interactions or even some pairwise interactions. Whether it is necessary to consider all higher-order interactions, and whether it is with little loss to replace them by lower-order or even pairwise interactions, remain a controversial issue. If the role of higher-order interactions is insignificant, the complexity of computation and the difficulty of analysis can be drastically reduced by projecting higher-order interactions into lower-order or pairwise interactions. We use link prediction, a fundamental problem in network science, as the entry point. Specifically, we evaluate the impact of higher-order interactions on link predictive accuracy to explore the necessity of these structures. We propose a method to decompose the higher-order structures in a stepwise way, thereby allowing to systematically explore the impacts of structures at different orders on link prediction. The results indicate that in some networks, incorporating higher-order interactions significantly enhances the accuracy of link prediction, while in others, the effect is insignificant. Therefore, we think that the role of higher-order interactions varies in different types of networks. Overall, since the improvement in predictive accuracy provided by higher-order interactions is significant in some networks, we believe that the study of higher-order interactions is both necessary and valuable.

physics.soc-ph↗

arXiv2024

Quantifying discriminability of evaluation metrics in link prediction for real networks

Link prediction is one of the most productive branches in network science, aiming to predict links that would have existed but have not yet been observed, or links that will appear during the evolution of the network. Over nearly two decades, the field of link prediction has amassed a substantial body of research, encompassing a plethora of algorithms and diverse applications. For any algorithm, one or more evaluation metrics are required to assess its performance. Because using different evaluation metrics can provide different assessments of the algorithm performance, how to select appropriate evaluation metrics is a fundamental issue in link prediction. To address this issue, we propose a novel measure that quantifiers the discriminability of any evaluation metric given a real network and an algorithm. Based on 131 real networks and 20 representative algorithms, we systematically compare the discriminabilities of eight evaluation metrics, and demonstrate that H-measure and Area Under the ROC Curve (AUC) exhibit the strongest discriminabilities, followed by Normalized Discounted Cumulative Gain (NDCG). Our finding is robust for networks in different domains and algorithms of different types. This study provides insights into the selection of evaluation metrics, which may further contribute to standardizing the evaluating process of link prediction algorithms.

cs.SI↗

arXiv2024

Inconsistency of evaluation metrics in link prediction

Link prediction is a paradigmatic and challenging problem in network science, which aims to predict missing links, future links and temporal links based on known topology. Along with the increasing number of link prediction algorithms, a critical yet previously ignored risk is that the evaluation metrics for algorithm performance are usually chosen at will. This paper implements extensive experiments on hundreds of real networks and 25 well-known algorithms, revealing significant inconsistency among evaluation metrics, namely different metrics probably produce remarkably different rankings of algorithms. Therefore, we conclude that any single metric cannot comprehensively or credibly evaluate algorithm performance. Further analysis suggests the usage of at least two metrics: one is the area under the receiver operating characteristic curve (AUC), and the other is one of the following three candidates, say the area under the precision-recall curve (AUPR), the area under the precision curve (AUC-Precision), and the normalized discounted cumulative gain (NDCG). In addition, as we have proved the essential equivalence of threshold-dependent metrics, if in a link prediction task, some specific thresholds are meaningful, we can consider any one threshold-dependent metric with those thresholds. This work completes a missing part in the landscape of link prediction, and provides a starting point toward a well-accepted criterion or standard to select proper evaluation metrics for link prediction.

cs.SI↗

arXiv2024

Comparing discriminating abilities of evaluation metrics in link prediction

Link prediction aims to predict the potential existence of links between two unconnected nodes within a network based on the known topological characteristics. Evaluation metrics are used to assess the effectiveness of algorithms in link prediction. The discriminating ability of these evaluation metrics is vitally important for accurately evaluating link prediction algorithms. In this study, we propose an artificial network model, based on which one can adjust a single parameter to monotonically and continuously turn the prediction accuracy of the specifically designed link prediction algorithm. Building upon this foundation, we show a framework to depict the effectiveness of evaluating metrics by focusing on their discriminating ability. Specifically, a quantitative comparison in the abilities of correctly discerning varying prediction accuracies was conducted encompassing nine evaluation metrics: Precision, Recall, F1-Measure, Matthews Correlation Coefficient (MCC), Balanced Precision (BP), the Area Under the receiver operating characteristic Curve (AUC), the Area Under the Precision-Recall curve (AUPR), Normalized Discounted Cumulative Gain (NDCG), and the Area Under the magnified ROC (AUC-mROC). The results indicate that the discriminating abilities of the three metrics, AUC, AUPR, and NDCG, are significantly higher than those of other metrics.

cs.SI↗