Detecting User Community in Sparse Domain via Cross-Graph Pairwise Learning

  title={Detecting User Community in Sparse Domain via Cross-Graph Pairwise Learning},
  author={Zheng Gao and Hongsong Li and Zhuoren Jiang and Xiaozhong Liu},
  journal={Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval},
  • Zheng Gao, Hongsong Li, +1 author Xiaozhong Liu
  • Published 25 July 2020
  • Computer Science
  • Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
Cyberspace hosts abundant interactions between users and different kinds of objects, and their relations are often encapsulated as bipartite graphs. Detecting user community in such heterogeneous graphs is an essential task to uncover user information needs and to further enhance recommendation performance. While several main cyber domains carrying high-quality graphs, unfortunately, most others can be quite sparse. However, as users may appear in multiple domains (graphs), their high-quality… 
Paraphrase Label Alignment for Voice Application Retrieval in Spoken Language Understanding
This work proposes a two-step approach to automatically align claimed utterance labels to unclaimed utterances, and demonstrates that the proposed model significantly outperforms a number of strong alternatives.
Improving Community Detection Performance in Heterogeneous Music Network by Learning Edge-type Usefulness Distribution
A genetic based approach to learn an edge-type usefulness distribution (ETUD) for all edge-types in heterogeneous music networks can be regarded as a linear function to project all edges to the same latent space and make them comparable.


Efficient personalized community detection via genetic evolution
A genetic model including an offline and an online step is proposed to solve the personalized community detection task in an efficient way and outperforms the state-of-arts with significantly reduced running time.
Do more views of a graph help? Community detection and clustering in multi-graphs
This work proposes Multi-CLUS and GraphFuse, two multi-graph clustering techniques powered by Minimum Description Length and Tensor analysis, respectively, and demonstrates higher clustering accuracy than state-of-the-art baselines that do not exploit the multi-view nature of the network data.
Overlapping community detection at scale: a nonnegative matrix factorization approach
This paper presents BIGCLAM (Cluster Affiliation Model for Big Networks), an overlapping community detection method that scales to large networks of millions of nodes and edges and builds on a novel observation that overlaps between communities are densely connected.
Flexible and robust co-regularized multi-domain graph clustering
CGC (Co-regularized Graph Clustering), based on non-negative matrix factorization (NMF), has several advantages over the existing methods, and provides users with the extent to which the cross-domain instance relationship violates the in-domain clustering structure, and thus enables users to re-evaluate the consistency of the relationship.
Detecting Local Community Structures in Social Networks Using Concept Interestingness
A novel strategy called COIN is introduced, which exploits COncept INterestingness measures to detect communities based on the concept lattice construction of the network, and can quickly detect communities more accurately than existing prominent algorithms such as Edge betweenness, Fast greedy modularity, and Infomap.
Real-time community detection in full social networks on a laptop
This article presents an approach for analyzing full social networks on a standard laptop, allowing for interactive exploration of the communities in the locality of a set of user specified query vertices and achieves single-machine real-time performance by compressing the neighborhood of each vertex using minhash signatures and facilitating rapid queries through Locality Sensitive Hashing.
Cross-Domain Recommendation via Clustering on Multi-Layer Graphs
This work introduces a novel cross-network collaborative recommendation framework C3R, which utilizes both individual and group knowledge, while being trained on data from multiple social media sources, and suggests a new approach for automatic construction of inter-network relationship graph based on the data, which eliminates the necessity of having pre-defined domain knowledge.
Deep Multi-Graph Clustering via Attentive Cross-Graph Association
An end-to-end deep learning model is proposed to simultaneously infer cluster assignments and cluster associations in multi-graph using autoencoding networks to learn node embeddings and a minimum-entropy based clustering strategy to cluster nodes in the embedding space for each graph.
Personalized community detection in scholarly network
This work introduces a personalized community detection algorithm that provides higher-resolution partitioning of areas of the network that are more relevant to a provided seed query and can produce a more fine-tuned partition of a scholarly network when compared to existing prior-insensitive approaches.