Rong Zhou

Rong Zhou

Auto-generated profile, based on publicly available information

Rong Zhou

Google, Mountain View, CA, USA

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2018 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Open access
RRRyan Rossi
Ryan Rossi
RZRong Zhou
Rong Zhou
NANesreen K. Ahmed
Nesreen K. Ahmed
This paper presents a general inductive graph representation learning framework called DeepGL for learning deep node and edge features that generalize across-networks. In particular, DeepGL begins by deriving a set of base features from the graph (e.g., graphlet features) and automatically learns a multi-layered hierarchical graph representation where each successive layer leverages the output from the previous layer to learn features of a higher-order. Contrary to previous work, DeepGL learns relational functions (each representing a feature) that naturally generalize across-networks and are therefore useful for graph-based transfer learning tasks. Moreover, DeepGL naturally supports attributed graphs, learns interpretable inductive graph representations, and is space-efficient (by learning sparse feature vectors). In addition, DeepGL is expressive, flexible with many interchangeable components, efficient with a time complexity of $O(|E|)$ , and scalable for large networks via an efficient parallel implementation. Compared with recent methods, DeepGL is (1) effective for across-network transfer learning tasks and large (attributed) graphs, (2) space-efficient requiring up to 6x less memory, (3) fast with up to 106x speedup in runtime performance, and (4) accurate with an average improvement in AUC of 20% or more on many learning tasks and across a wide variety of networks.

2 July 2020 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
NANesreen K. Ahmed
Nesreen K. Ahmed
RRRyan Rossi
Ryan Rossi
JLJohn Boaz Lee
John Boaz Lee
TWTheodore L. Willke
Theodore L. Willke
RZRong Zhou
Rong Zhou
HEHoda Eldardiry
Hoda Eldardiry
Random walks are at the heart of many existing node embedding and network representation learning methods. However, such methods have many limitations that arise from the use of traditional random walks, e.g., the embeddings resulting from these methods capture proximity (communities) among the vertices as opposed to structural similarity (roles). Furthermore, the embeddings are unable to transfer to new nodes and graphs as they are tied to node identity. To overcome these limitations, we introduce the Role2Vec framework based on the proposed notion of attributed random walks to learn structural role-based embeddings. Notably, the framework serves as a basis for generalizing any walk-based method. The Role2Vec framework enables these methods to be more widely applicable by learning inductive functions that capture the structural roles in the graph. Furthermore, the original methods are recovered as a special case of the framework when each vertex is mapped to its own function that uniquely identifies it. Finally, the Role2Vec framework is shown to be effective with an average AUC improvement of 17.8 percent for link prediction while requiring on average 853x less space than existing methods on a variety of graphs from different domains.

18 May 2018 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Open access
RRRyan Rossi
Ryan Rossi
RZRong Zhou
Rong Zhou
NANesreen K. Ahmed
Nesreen K. Ahmed
Graphlets are induced subgraphs of a large network and are important for understanding and modeling complex networks. Despite their practical importance, graphlets have been severely limited to applications and domains with relatively small graphs. Most previous work has focused on exact algorithms; however, it is often too expensive to compute graphlets exactly in massive networks with billions of edges, and finding an approximate count is usually sufficient for many applications. In this paper, we propose an unbiased graphlet estimation framework that is: (a) fast with large speedups compared to the state of the art; (b) parallel with nearly linear speedups; (c) accurate with less than 1% relative error; (d) scalable and space efficient for massive networks with billions of edges; and (e) effective for a variety of real-world settings as well as estimating global and local graphlet statistics (e.g., counts). On 300 networks from 20 domains, we obtain <1% relative error for all graphlets. This is vastly more accurate than the existing methods while using less data. Moreover, it takes a few seconds on billion edge graphs (as opposed to days/weeks). These are by far the largest graphlet computations to date.

23 November 2017 in arXiv
Verified
Preprint
Open access
PDF file
NANesreen K. Ahmed
Nesreen K. Ahmed
RRRyan A. Rossi
Ryan A. Rossi
RZRong Zhou
Rong Zhou
JLJohn Boaz Lee
John Boaz Lee
XKXiangnan Kong
Xiangnan Kong
HEHoda Eldardiry
Hoda Eldardiry
Graphs (networks) are ubiquitous and allow us to model entities (nodes) and the dependencies (edges) between them. Learning a useful feature representation from graph data lies at the heart and success of many machine learning tasks such as classification, anomaly detection, link prediction, among many others. Many existing techniques use random walks as a basis for learning features or estimating the parameters of a graph model for a downstream prediction task. Examples include recent node embedding methods such as DeepWalk, node2vec, as well as graph-based deep learning algorithms. However, the simple random walk used by these methods is fundamentally tied to the identity of the node. This has three main disadvantages. First, these approaches are inherently transductive and do not generalize to unseen nodes and other graphs. Second, they are not space-efficient as a feature vector is learned for each node which is impractical for large graphs. Third, most of these approaches lack support for attributed graphs. To make these methods more generally applicable, we propose a framework for inductive network representation learning based on the notion of attributed random walk that is not tied to node identity and is instead based on learning a function $\Phi : \mathrm{\rm \bf x} \rightarrow w$ that maps a node attribute vector $\mathrm{\rm \bf x}$ to a type $w$. This framework serves as a basis for generalizing existing methods such as DeepWalk, node2vec, and many other previous methods that leverage traditional random walks.

1 September 2013 in AI Magazine
Verified
Journal Article
Closed access
PDF file
LCLara S. Crawford
Lara S. Crawford
MDMinh Binh Do
Minh Binh Do
WRWheeler S. Ruml
Wheeler S. Ruml
HHHaitham Hindi
Haitham Hindi
CECraig Eldershaw
Craig Eldershaw
DLDaniel Larner
Daniel Larner
A recent trend in intelligent machines and manufacturing has been toward reconfigurable manufacturing systems. Such systems move away from a fixed factory line executing an unchanging set of operations and toward the goal of an adaptable factory structure. The logical next challenge in this area is that of online reconfigurability. With this capability, machines can reconfigure while running, enable or disable capabilities in real time, and respond quickly to changes in the system or the environment (including faults). We propose an approach to achieving online reconfigurability based on a high level of system modularity supported by integrated, model‐based planning and control software. Our software capitalizes on many advanced techniques from the artificial intelligence research community, particularly in model‐based domain‐independent planning and scheduling, heuristic search, and temporal resource reasoning. We describe the implementation of this design in a prototype highly modular, parallel printing system.

1 October 2015
Verified
Conference Paper
Closed access
RRRyan Rossi
Ryan Rossi
RZRong Zhou
Rong Zhou
Relational models for heterogeneous network data are becoming increasingly important for many real-world applications. However, existing relational learning approaches are not parallel, have scalability issues, and thus unable to handle large heterogeneous network data. In this paper, we propose Parallel Collective Matrix Factorization (PCMF) that serves as a fast and flexible framework for joint modeling of large heterogeneous networks. The PCMF learning algorithm solves for a single parameter given the others, leading to a parallel scheme that is fast, flexible, and general for a variety of relational learning tasks and heterogeneous data types. The proposed approach is carefully designed to be (a) efficient for large heterogeneous networks (linear in the total number of observations from the set of input matrices), (b) flexible as many components are interchangeable and easily adaptable, and (c) effective for a variety of applications as well as for different types of data. The experiments demonstrate the scalability, flexibility, and effectiveness of PCMF. For instance, we show that PCMF outperforms a recent state-of-the-art parallel approach in runtime, scalability, and prediction quality. Finally, the effectiveness of PCMF is shown on a number of relational learning tasks such as serving predictions in a realtime streaming fashion.