skip to main content


The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Friday, September 29 until 11:59 PM ET on Saturday, September 30 due to maintenance. We apologize for the inconvenience.

Search for: All records

Creators/Authors contains: "Hanghang, Tong"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Graph neural networks (GNNs) have achieved tremendous success in many graph learning tasks such as node classifica- tion, graph classification and link prediction. For the classifi- cation task, GNNs’ performance often highly depends on the number of labeled nodes and thus could be significantly ham- pered due to the expensive annotation cost. The sparse litera- ture on active learning for GNNs has primarily focused on se- lecting only one sample each iteration, which becomes ineffi- cient for large scale datasets. In this paper, we study the batch active learning setting for GNNs where the learning agent can acquire labels of multiple samples at each time. We formu- late batch active learning as a cooperative multi-agent rein- forcement learning problem and present a novel reinforced batch-mode active learning framework (BIGENE). To avoid the combinatorial explosion of the joint action space, we in- troduce a value decomposition method that factorizes the to- tal Q-value into the average of individual Q-values. More- over, we propose a novel multi-agent Q-network consisting of a graph convolutional network (GCN) component and a gated recurrent unit (GRU) component. The GCN compo- nent takes both the informativeness and inter-dependences between nodes into account and the GRU component enables the agent to consider interactions between selected nodes in the same batch. Experimental results on multiple public datasets demonstrate the effectiveness and efficiency of our proposed method. 
    more » « less
  2. Clique-counting is a fundamental problem that has application in many areas eg. dense subgraph discovery, community detection, spam detection, etc. The problem of k-clique-counting is difficult because as k increases, the number of k-cliques goes up exponentially. Enumeration algorithms (even parallel ones) fail to count k-cliques beyond a small k. Approximation algorithms, like TuránShadow have been shown to perform well upto k = 10, but are inefficient for larger cliques. The recently proposed Pivoter algorithm significantly improved the state-of-the-art and was able to give exact counts of all k-cliques in a large number of graphs. However, the clique counts of some graphs (for example, com-lj) are still out of reach of these algorithms. We revisit the TuránShadow algorithm and propose a generalized framework called YACC that leverages several insights about real-world graphs to achieve faster clique-counting. The bottleneck in TuránShadow is a recursive subroutine whose stopping condition is based on a classic result from extremal combinatorics called Turán's theorem. This theorem gives a lower bound for the k-clique density in a subgraph in terms of its edge density. However, this stopping condition is based on a worst-case graph that does not reflect the nature of real-world graphs. Using techniques for quickly discovering dense subgraphs, we relax the stopping condition in a systematic way such that we get a smaller recursion tree while still maintaining the guarantees provided by TuránShadow. We deploy our algorithm on several real-world data sets and show that YACC reduces the size of the recursion tree and the running time by over an order of magnitude. Using YACC, we are able to obtain clique counts for several graphs for which clique-counting was infeasible before, including com-lj. 
    more » « less
  3. null (Ed.)
    Co-evolving time series appears in a multitude of applications such as environmental monitoring, financial analysis, and smart transportation. This paper aims to address the following three challenges, including (C1) how to effectively model its multi-mode tensor structure at each time step; (C2) how to incorporate explicit relationship networks of the time series; (C3) how to model the implicit relationship of the temporal dynamics. We propose a novel model called Network of Tensor Time Series, which is comprised of two modules, including Tensor Graph Convolutional Network (TGCN) and Tensor Recurrent Neural Network (TRNN). TGCN tackles the first two challenges by generalizing Graph Convolutional Network (GCN) for flat graphs to tensor graphs, which captures the synergy between multiple graphs associated with the tensors. TRNN leverages tensor decomposition to balance the trade-off between the commonality and specificity of the co-evolving time series. The experimental results on five real-world datasets demonstrate the efficacy of the proposed method. 
    more » « less
  4. 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
  5. This paper presents a novel algorithm for recovering missing values of co-evolving time series with partial embedded network information. The idea is to connect two sources of data (time series data and embedded network data) through a shared low dimensional latent space. The proposed algorithm, named NetDyna, is an Expectation-Maximization (EM) algorithm, and uses the Kalman filter and matrix factorization approaches to infer the missing values both in the time series and embedded network. Our experimental results on real datasets, including a Motes dataset and a Motion Capture dataset, show that (1) NetDyna outperforms other state-of-the-art algorithms, especially with partially observed network information; (2) its computational complexity scales linearly with the time duration of time series; and (3) the algorithm recovers the embedded network in addition to missing time series values. 
    more » « less
  6. Suppose certain data points are overly contaminated, then the existing principal component analysis (PCA) methods are frequently incapable of filtering out and eliminating the excessively polluted ones, which potentially lead to the functional degeneration of the corresponding models. To tackle the issue, we propose a general framework namely robust weight learning with adaptive neighbors (RWL-AN), via which adaptive weight vector is automatically obtained with both robustness and sparse neighbors. More significantly, the degree of the sparsity is steerable such that only exact k well-fitting samples with least reconstruction errors are activated during the optimization, while the residual samples, i.e., the extreme noised ones are eliminated for the global robustness. Additionally, the framework is further applied to PCA problem to demonstrate the superiority and effectiveness of the proposed RWL-AN model. 
    more » « less
  7. Geographic information provides an important insight into many data mining and social media systems. However, users are reluctant to provide such information due to various concerns, such as inconvenience, privacy, etc. In this paper, we aim to develop a deep learning based solution to predict geographic information for tweets. The current approaches bear two major limitations, including (a) hard to model the long term information and (b) hard to explain to the end users what the model learns. To address these issues, our proposed model embraces three key ideas. First, we introduce a multi-head self-attention model for text representation. Second, to further improve the result on informal language, we treat subword as a feature in our model. Lastly, the model is trained jointly with the city and country to incorporate the information coming from different labels. The experiment performed on W-NUT 2016 Geo-tagging shared task shows our proposed model is competitive with the state-of-the-art systems when using accuracy measurement, and in the meanwhile, leading to a better distance measure over the existing approaches. 
    more » « less