More Like this

1. Co-Embedding Network Nodes and Hierarchical Labels with Taxonomy Based Generative Adversarial Networks

   https://doi.org/10.1109/ICDM50108.2020.00081  

   Yang, Carl ; Zhang, Jieyu ; Han, Jiawei ( November 2020 , ICDM'20: IEEE 2020 Int. Conf. on Data Mining, Nov. 2020)

   null (Ed.)

   Network embedding aims at transferring node proximity in networks into distributed vectors, which can be leveraged in various downstream applications. Recent research has shown that nodes in a network can often be organized in latent hierarchical structures, but without a particular underlying taxonomy, the learned node embedding is less useful nor interpretable. In this work, we aim to improve network embedding by modeling the conditional node proximity in networks indicated by node labels residing in real taxonomies. In the meantime, we also aim to model the hierarchical label proximity in the given taxonomies, which is too coarse by solely looking at the hierarchical topologies. To this end, we propose TAXOGAN to co-embed network nodes and hierarchical labels, through a hierarchical network generation process. Particularly, TAXOGAN models the child labels and network nodes of each parent label in an individual embedding space while learning to transfer network proximity among the spaces of hierarchical labels through stacked network generators and embedding encoders. To enable robust and efficient model inference, we further develop a hierarchical adversarial training process. Comprehensive experiments and case studies on four real-world datasets of networks with hierarchical labels demonstrate the utility of TAXOGAN in improving network embedding on traditional tasks of node classification and link prediction, as well as novel tasks like conditional proximity search and fine-grained taxonomy layout. 

   more » « less
2. TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering

   https://doi.org/10.1145/3219819.3220064  

   Zhang, Chao ; Tao, Fangbo ; Chen, Xiusi ; Shen, Jiaming ; Jiang, Meng ; Sadler, Brian ; Vanni, Michelle ; Han, Jiawei ( August 2018 , Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2018)

   Taxonomy construction is not only a fundamental task for semantic analysis of text corpora, but also an important step for applications such as information filtering, recommendation, and Web search. Existing pattern-based methods extract hypernym-hyponym term pairs and then organize these pairs into a taxonomy. However, by considering each term as an independent concept node, they overlook the topical proximity and the semantic correlations among terms. In this paper, we propose a method for constructing topic taxonomies, wherein every node represents a conceptual topic and is defined as a cluster of semantically coherent concept terms. Our method, TaxoGen, uses term embeddings and hierarchical clustering to construct a topic taxonomy in a recursive fashion. To ensure the quality of the recursive process, it consists of: (1) an adaptive spherical clustering module for allocating terms to proper levels when splitting a coarse topic into fine-grained ones; (2) a local embedding module for learning term embeddings that maintain strong discriminative power at different levels of the taxonomy. Our experiments on two real datasets demonstrate the effectiveness of TaxoGen compared with baseline methods. 

   more » « less
3. Node, Motif and Subgraph: Leveraging Network Functional Blocks Through Structural Convolution

   https://doi.org/10.1109/ASONAM.2018.8508729  

   Yang, Carl ; Liu, Mengxiong ; Zheng, Vincent W. ; Han, Jiawei ( August 2018 , IEEE/ACM 2018 International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018)

   Networks or graphs provide a natural and generic way for modeling rich structured data. Recent research on graph analysis has been focused on representation learning, of which the goal is to encode the network structures into distributed embedding vectors, so as to enable various downstream applications through off-the-shelf machine learning. However, existing methods mostly focus on node-level embedding, which is insufficient for subgraph analysis. Moreover, their leverage of network structures through path sampling or neighborhood preserving is implicit and coarse. Network motifs allow graph analysis in a finer granularity, but existing methods based on motif matching are limited to enumerated simple motifs and do not leverage node labels and supervision. In this paper, we develop NEST, a novel hierarchical network embedding method combining motif filtering and convolutional neural networks. Motif-based filtering enables NEST to capture exact small structures within networks, and convolution over the filtered embedding allows it to fully explore complex substructures and their combinations. NEST can be trivially applied to any domain and provide insight into particular network functional blocks. Extensive experiments on protein function prediction, drug toxicity prediction and social network community identification have demonstrated its effectiveness and efficiency. 

   more » « less
4. Toward Understanding and Evaluating Structural Node Embeddings

   https://doi.org/10.1145/3481639  

   Jin, Junchen ; Heimann, Mark ; Jin, Di ; Koutra, Danai ( June 2022 , ACM Transactions on Knowledge Discovery from Data)

   While most network embedding techniques model the proximity between nodes in a network, recently there has been significant interest in structural embeddings that are based on node equivalences , a notion rooted in sociology: equivalences or positions are collections of nodes that have similar roles—i.e., similar functions, ties or interactions with nodes in other positions—irrespective of their distance or reachability in the network. Unlike the proximity-based methods that are rigorously evaluated in the literature, the evaluation of structural embeddings is less mature. It relies on small synthetic or real networks with labels that are not perfectly defined, and its connection to sociological equivalences has hitherto been vague and tenuous. With new node embedding methods being developed at a breakneck pace, proper evaluation, and systematic characterization of existing approaches will be essential to progress. To fill in this gap, we set out to understand what types of equivalences structural embeddings capture. We are the first to contribute rigorous intrinsic and extrinsic evaluation methodology for structural embeddings, along with carefully-designed, diverse datasets of varying sizes. We observe a number of different evaluation variables that can lead to different results (e.g., choice of similarity measure, classifier, and label definitions). We find that degree distributions within nodes’ local neighborhoods can lead to simple yet effective baselines in their own right and guide the future development of structural embedding. We hope that our findings can influence the design of further node embedding methods and also pave the way for more comprehensive and fair evaluation of structural embedding methods. 

   more » « less
5. 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