More Like this

1. Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks

   Jin, Bowen; Zhang, Yu; Meng, Yu; Han, Jiawei (May 2023, The Eleventh International Conference on Learning Representations, {ICLR} 2023)

   Edges in many real-world social/information networks are associated with rich text information (e.g., user-user communications or user-product reviews). However, mainstream network representation learning models focus on propagating and aggregating node attributes, lacking specific designs to utilize text semantics on edges. While there exist edge-aware graph neural networks, they directly initialize edge attributes as a feature vector, which cannot fully capture the contextualized text semantics of edges. In this paper, we propose Edgeformers, a framework built upon graph-enhanced Transformers, to perform edge and node representation learning by modeling texts on edges in a contextualized way. Specifically, in edge representation learning, we inject network information into each Transformer layer when encoding edge texts; in node representation learning, we aggregate edge representations through an attention mechanism within each node’s ego-graph. On five public datasets from three different domains, Edgeformers consistently outperform state-of-the-art baselines in edge classification and link prediction, demonstrating the efficacy in learning edge and node representations, respectively. 

   more » « less
2. Rapid and Precise Topological Comparison with Merge Tree Neural Networks

   https://doi.org/10.1109/TVCG.2024.3456395  

   Qin, Yu; Fasy, Brittany Terese; Wenk, Carola; Summa, Brian (September 2024, IEEE Transactions on Visualization and Computer Graphics)

   Merge trees are a valuable tool in the scientific visualization of scalar fields; however, current methods for merge tree comparisons are computationally expensive, primarily due to the exhaustive matching between tree nodes. To address this challenge, we introduce the Merge Tree Neural Network (MTNN), a learned neural network model designed for merge tree comparison. The MTNN enables rapid and high-quality similarity computation. We first demonstrate how to train graph neural networks, which emerged as effective encoders for graphs, in order to to produce embeddings of merge trees in vector spaces for efficient similarity comparison. Next, we formulate the novel MTNN model that further improves the similarity comparisons by integrating the tree and node embeddings with a new topological attention mechanism. We demonstrate the effectiveness of our model on real-world data in different domains and examine our model's generalizability across various datasets. Our experimental analysis demonstrates our approach's superiority in accuracy and efficiency. In particular, we speed up the prior state-of-the-art by more than 100x on the benchmark datasets while maintaining an error rate below 0.1%. 

   more » « less
3. NetTrans: Neural Cross-Network Transformation

   https://doi.org/doi.org/10.1145/3394486.3403141  

   Si Zhang, Hanghang Tong (August 2020, KDD '20: Proceedings of the 26th ACM SIGKKDD International Conference on Knowledge Discovery & Data Mining)

   null (Ed.)

   Finding node associations across different networks is the cornerstone behind a wealth of high-impact data mining applications. Traditional approaches are often, explicitly or implicitly, built upon the linearity and/or consistency assumptions. On the other hand, the recent network embedding based methods promise a natural way to handle the non-linearity, yet they could suffer from the disparate node embedding space of different networks. In this paper, we address these limitations and tackle cross-network node associations from a new angle, i.e., cross-network transformation. We ask a generic question: Given two different networks, how can we transform one network to another? We propose an end-to-end model that learns a composition of nonlinear operations so that one network can be transformed to another in a hierarchical manner. The proposed model bears three distinctive advantages. First (composite transformation), it goes beyond the linearity/consistency assumptions and performs the cross-network transformation through a composition of nonlinear computations. Second (representation power), it can learn the transformation of both network structures and node attributes at different resolutions while identifying the cross-network node associations. Third (generality), it can be applied to various tasks, including network alignment, recommendation, cross-layer dependency inference. Extensive experiments on different tasks validate and verify the effectiveness of the proposed model. 

   more » « less
4. Bringing Order to Network Embedding: A Relative Ranking based Approach

   https://doi.org/10.1145/3340531.3412041  

   Wang, Yaojing; Pan, Guosheng; Yao, Yuan; Tong, Hanghang; Yang, Hongxia; Xu, Feng; Lu, Jian (October 2020, CIKM'20)

   null (Ed.)

   Network embedding aims to automatically learn the node representations in networks. The basic idea of network embedding is to first construct a network to describe the neighborhood context for each node, and then learn the node representations by designing an objective function to preserve certain properties of the constructed context network. The vast majority of the existing methods, explicitly or implicitly, follow a pointwise design principle. That is, the objective can be decomposed into the summation of the certain goodness function over each individual edge of the context network. In this paper, we propose to go beyond such pointwise approaches, and introduce the ranking-oriented design principle for network embedding. The key idea is to decompose the overall objective function into the summation of a goodness function over a set of edges to collectively preserve their relative rankings on the context network. We instantiate the ranking-oriented design principle by two new network embedding algorithms, including a pairwise network embedding method PaWine which optimizes the relative weights of edge pairs, and a listwise method LiWine which optimizes the relative weights of edge lists. Both proposed algorithms bear a linear time complexity, making themselves scalable to large networks. We conduct extensive experimental evaluations on five real datasets with a variety of downstream learning tasks, which demonstrate that the proposed approaches consistently outperform the existing methods. 

   more » « less
5. Mutual Information Measure for Glass Ceiling Effect in Preferential Attachment Models

   https://doi.org/10.1109/TCSS.2024.3432600  

   Luo, Rui; Nettasinghe, Buddhika; Krishnamurthy, Vikram (December 2024, IEEE Transactions on Computational Social Systems)

   This article introduces a novel mutual informationbased measure to assess the glass ceiling effect in preferential attachment networks, which advances the analysis of inequalities in attributed networks. Using Shannon entropy and generalizing to Rényi entropy, our measure evaluates the conditional probability distributions of node attributes given the node degrees of adjacent nodes, which offers a more nuanced understanding of inequality compared to traditional methods that emphasize node degree distributions and degree assortativity alone. To evaluate the efficacy of the proposed measure, we evaluate it using an analytical structural inequality model as well as historical publication data. Results show that our mutual information measure aligns well with both the theoretical model and empirical data, underscoring its reliability as a robust approach for capturing inequalities in attributed networks. Moreover, we introduce a novel stochastic optimization algorithm that utilizes a parameterized conditional logit model for edge addition. Our algorithm is shown to outperform the baseline uniform distribution based approach in mitigating the glass ceiling effect. By strategically recommending links based on this algorithm, we can effectively hinder the glass ceiling effect within networks. 

   more » « less