Hao Ding
Purdue University
23 Papers
35 Citations
Hao Ding is an academic researcher from Purdue University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 10, co-authored 16 publications. Previous affiliations of Hao Ding include Beijing University of Posts and Telecommunications & Amazon.com.
Chat about Author
Papers
SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
Yunsheng Bai,Hao Ding,Song Bian,Ting Chen,Yizhou Sun,Wei Wang +5 more
- 30 Jan 2019
TL;DR: This work proposes a novel neural network based approach to address this classic yet challenging graph problem, aiming to alleviate the computational burden while preserving a good performance, and suggests SimGNN provides a new direction for future research on graph similarity computation and graph similarity search.
348
Learning-Based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching
Yunsheng Bai,Hao Ding,Ken Gu,Yizhou Sun,Wei Wang +4 more
- 03 Apr 2020
TL;DR: The model, Graph-Sim, achieves the state-of-the-art performance on four real-world graph datasets under six out of eight settings, compared to existing popular methods for approximate Graph Edit Distance (GED) and Maximum Common Subgraph (MCS) computation.
Temporal-Contextual Recommendation in Real-Time
Yifei Ma,Balakrishnan Narayanaswamy,Haibin Lin,Hao Ding +3 more
- 23 Aug 2020
TL;DR: This work presents a black-box recommender system that can adapt to a diverse set of scenarios without the need for manual tuning, and introduces a compact model, which is called hierarchical recurrent network with meta data (HRNN-meta) to address the real-time and diverse metadata needs.
Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
Yunsheng Bai,Hao Ding,Yang Qiao,Agustin Marinovic,Ken Gu,Ting Chen,Yizhou Sun,Wei Wang +7 more
- 01 Aug 2019
TL;DR: UGRAPHEMB is a general framework that provides a novel means to performing graph-level embedding in a completely unsupervised and inductive manner and achieves competitive accuracy in the tasks of graph classification, similarity ranking, and graph visualization.
•Posted Content
SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
TL;DR: SimGNN as mentioned in this paper proposes a learnable embedding function that maps every graph into a vector, which provides a global summary of a graph, and a pairwise node comparison method to supplement the graph-level embeddings with fine-grained node-level information.
59