Search

We investigate graph representation learning approaches that enable models to generalize across graphs: given a model trained using the representations from one graph, our goal is to apply inference using those same model parameters when given representations computed over a new graph, unseen during model training, with minimal degradation in inference accuracy. This is in contrast to the more common task of doing inference on the unseen nodes of the same graph. We show that using random projections to estimate multiple powers of the transition matrix allows us to build a set of isomorphism-invariant features that can be used by a variety of tasks. The resulting features can be used to recover enough information about the local neighborhood of a node to enable inference with relevance competitive to other approaches while maintaining computational efficiency.

Most work in graph-based recommender systems considers a {\em static} setting where all information about test nodes (i.e., users and items) is available upfront at training time. However, this static setting makes little sense for many real-world applications where data comes in continuously as a stream of new edges and nodes, and one has to update model predictions incrementally to reflect the latest state. To fully capitalize on the newly available data in the stream, recent graph-based recommendation models would need to be repeatedly retrained, which is infeasible in practice. In this paper, we study the graph-based streaming recommendation setting and propose a compositional recommendation model -- Lightweight Compositional Embedding (LCE) -- that supports incremental updates under low computational cost. Instead of learning explicit embeddings for the full set of nodes, LCE learns explicit embeddings for only a subset of nodes and represents the other nodes {\em implicitly}, through a composition function based on their interactions in the graph. This provides an effective, yet efficient, means to leverage streaming graph data when one node type (e.g., items) is more amenable to static representation. We conduct an extensive empirical study to compare LCE to a set of competitive baselines on three large-scale user-item recommendation datasets with interactions under a streaming setting. The results demonstrate the superior performance of LCE, showing that it achieves nearly skyline performance with significantly fewer parameters than alternative graph-based models.

Many resource management problems require sequential decision-making under uncertainty, where the only uncertainty affecting the decision outcomes are exogenous variables outside the control of the decision-maker. We model these problems as Exo-MDPs (Markov Decision Processes with Exogenous Inputs) and design a class of data-efficient algorithms for them termed Hindsight Learning (HL). Our HL algorithms achieve data efficiency by leveraging a key insight: having samples of the exogenous variables, past decisions can be revisited in hindsight to infer counterfactual consequences that can accelerate policy improvements. We compare HL against classic baselines in the multi-secretary and airline revenue management problems. We also scale our algorithms to a business-critical cloud resource management problem -- allocating Virtual Machines (VMs) to physical machines, and simulate their performance with real datasets from a large public cloud provider. We find that HL algorithms outperform domain-specific heuristics, as well as state-of-the-art reinforcement learning methods., Comment: 53 pages, 6 figures

Federated graph representation learning (FedGRL) brings the benefits of distributed training to graph structured data while simultaneously addressing some privacy and compliance concerns related to data curation. However, several interesting real-world graph data characteristics viz. label deficiency and downstream task heterogeneity are not taken into consideration in current FedGRL setups. In this paper, we consider a realistic and novel problem setting, wherein cross-silo clients have access to vast amounts of unlabeled data with limited or no labeled data and additionally have diverse downstream class label domains. We then propose a novel FedGRL formulation based on model interpolation where we aim to learn a shared global model that is optimized collaboratively using a self-supervised objective and gets downstream task supervision through local client models. We provide a specific instantiation of our general formulation using BGRL a SoTA self-supervised graph representation learning method and we empirically verify its effectiveness through realistic cross-slio datasets: (1) we adapt the Twitch Gamer Network which naturally simulates a cross-geo scenario and show that our formulation can provide consistent and avg. 6.1% gains over traditional supervised federated learning objectives and on avg. 1.7% gains compared to individual client specific self-supervised training and (2) we construct and introduce a new cross-silo dataset called Amazon Co-purchase Networks that have both the characteristics of the motivated problem setting. And, we witness on avg. 11.5% gains over traditional supervised federated learning and on avg. 1.9% gains over individually trained self-supervised models. Both experimental results point to the effectiveness of our proposed formulation. Finally, both our novel problem setting and dataset contributions provide new avenues for the research in FedGRL., Comment: FedGraph'22 workshop (non archival) version. (https://sites.google.com/view/fedgraph2022/accepted-papers)

Self-supervised learning of graph neural networks (GNN) is in great need because of the widespread label scarcity issue in real-world graph/network data. Graph contrastive learning (GCL), by training GNNs to maximize the correspondence between the representations of the same graph in its different augmented forms, may yield robust and transferable GNNs even without using labels. However, GNNs trained by traditional GCL often risk capturing redundant graph features and thus may be brittle and provide sub-par performance in downstream tasks. Here, we propose a novel principle, termed adversarial-GCL (AD-GCL), which enables GNNs to avoid capturing redundant information during the training by optimizing adversarial graph augmentation strategies used in GCL. We pair AD-GCL with theoretical explanations and design a practical instantiation based on trainable edge-dropping graph augmentation. We experimentally validate AD-GCL by comparing with the state-of-the-art GCL methods and achieve performance gains of up-to $14\%$ in unsupervised, $6\%$ in transfer, and $3\%$ in semi-supervised learning settings overall with 18 different benchmark datasets for the tasks of molecule property regression and classification, and social network classification., Accepted to NeurIPS 2021

Analyzing the readability of articles has been an important sociolinguistic task. Addressing this task is necessary to the automatic recommendation of appropriate articles to readers with different comprehension abilities, and it further benefits education systems, web information systems, and digital libraries. Current methods for assessing readability employ empirical measures or statistical learning techniques that are limited by their ability to characterize complex patterns such as article structures and semantic meanings of sentences. In this paper, we propose a new and comprehensive framework which uses a hierarchical self-attention model to analyze document readability. In this model, measurements of sentence-level difficulty are captured along with the semantic meanings of each sentence. Additionally, the sentence-level features are incorporated to characterize the overall readability of an article with consideration of article structures. We evaluate our proposed approach on three widely-used benchmark datasets against several strong baseline approaches. Experimental results show that our proposed method achieves the state-of-the-art performance on estimating the readability for various web articles and literature., Comment: ECIR 2020

Graph Neural Networks (GNNs) have recently been used for node and graph classification tasks with great success, but GNNs model dependencies among the attributes of nearby neighboring nodes rather than dependencies among observed node labels. In this work, we consider the task of inductive node classification using GNNs in supervised and semi-supervised settings, with the goal of incorporating label dependencies. Because current GNNs are not universal (i.e., most-expressive) graph representations, we propose a general collective learning approach to increase the representation power of any existing GNN. Our framework combines ideas from collective classification with self-supervised learning, and uses a Monte Carlo approach to sampling embeddings for inductive learning across graphs. We evaluate performance on five real-world network datasets and demonstrate consistent, significant improvement in node classification accuracy, for a variety of state-of-the-art GNNs.

Social Reinforcement Learning methods, which model agents in large networks, are useful for fake news mitigation, personalized teaching/healthcare, and viral marketing, but it is challenging to incorporate inter-agent dependencies into the models effectively due to network size and sparse interaction data. Previous social RL approaches either ignore agents dependencies or model them in a computationally intensive manner. In this work, we incorporate agent dependencies efficiently in a compact model by clustering users (based on their payoff and contribution to the goal) and combine this with a method to easily derive personalized agent-level policies from cluster-level policies. We also propose a dynamic clustering approach that captures changing user behavior. Experiments on real-world datasets illustrate that our proposed approach learns more accurate policy estimates and converges more quickly, compared to several baselines that do not use agent correlations or only use static clusters.

Clustering and community detection with multiple graphs have typically focused on aligned graphs, where there is a mapping between nodes across the graphs (e.g., multi-view, multi-layer, temporal graphs). However, there are numerous application areas with multiple graphs that are only partially aligned, or even unaligned. These graphs are often drawn from the same population, with communities of potentially different sizes that exhibit similar structure. In this paper, we develop a joint stochastic blockmodel (Joint SBM) to estimate shared communities across sets of heterogeneous non-aligned graphs. We derive an efficient spectral clustering approach to learn the parameters of the joint SBM. We evaluate the model on both synthetic and real-world datasets and show that the joint model is able to exploit cross-graph information to better estimate the communities compared to learning separate SBMs on each individual graph.

The goal of lifetime clustering is to develop an inductive model that maps subjects into $K$ clusters according to their underlying (unobserved) lifetime distribution. We introduce a neural-network based lifetime clustering model that can find cluster assignments by directly maximizing the divergence between the empirical lifetime distributions of the clusters. Accordingly, we define a novel clustering loss function over the lifetime distributions (of entire clusters) based on a tight upper bound of the two-sample Kuiper test p-value. The resultant model is robust to the modeling issues associated with the unobservability of termination signals, and does not assume proportional hazards. Our results in real and synthetic datasets show significantly better lifetime clusters (as evaluated by C-index, Brier Score, Logrank score and adjusted Rand index) as compared to competing approaches.

Research in statistical relational learning has produced a number of methods for learning relational models from large-scale network data. While these methods have been successfully applied in various domains, they have been developed under the unrealistic assumption of full data access. In practice, however, the data are often collected by crawling the network, due to proprietary access, limited resources, and privacy concerns. Recently, we showed that the parameter estimates for relational Bayes classifiers computed from network samples collected by existing network crawlers can be quite inaccurate, and developed a crawl-aware estimation method for such models (Yang, Ribeiro, and Neville, 2017). In this work, we extend the methodology to learning relational logistic regression models via stochastic gradient descent from partial network crawls, and show that the proposed method yields accurate parameter estimates and confidence intervals., 7 pages, 3 figures, Proceedings of the Seventh International Workshop on Statistical Relational AI (StarAI 2017)

The goal of cluster analysis in survival data is to identify clusters that are decidedly associated with the survival outcome. Previous research has explored this problem primarily in the medical domain with relatively small datasets, but the need for such a clustering methodology could arise in other domains with large datasets, such as social networks. Concretely, we wish to identify different survival classes in a social network by clustering the users based on their lifespan in the network. In this paper, we propose a decision tree based algorithm that uses a global normalization of $p$-values to identify clusters with significantly different survival distributions. We evaluate the clusters from our model with the help of a simple survival prediction task and show that our model outperforms other competing methods.

Gradient boosting of regression trees is a competitive procedure for learning predictive models of continuous data that fits the data with an additive non-parametric model. The classic version of gradient boosting assumes that the data is independent and identically distributed. However, relational data with interdependent, linked instances is now common and the dependencies in such data can be exploited to improve predictive performance. Collective inference is one approach to exploit relational correlation patterns and significantly reduce classification error. However, much of the work on collective learning and inference has focused on discrete prediction tasks rather than continuous. %target values has not got that attention in terms of collective inference. In this work, we investigate how to combine these two paradigms together to improve regression in relational domains. Specifically, we propose a boosting algorithm for learning a collective inference model that predicts a continuous target variable. In the algorithm, we learn a basic relational model, collectively infer the target values, and then iteratively learn relational models to predict the residuals. We evaluate our proposed algorithm on a real network dataset and show that it outperforms alternative boosting methods. However, our investigation also revealed that the relational features interact together to produce better predictions., Comment: 7 pages, 3 Figures, Sixth International Workshop on Statistical Relational AI

Bayesian networks (BNs) are used for inference and sampling by exploiting conditional independence among random variables. Context specific independence (CSI) is a property of graphical models where additional independence relations arise in the context of particular values of random variables (RVs). Identifying and exploiting CSI properties can simplify inference. Some generative network models (models that generate social/information network samples from a network distribution P(G)), with complex interactions among a set of RVs, can be represented with probabilistic graphical models, in particular with BNs. In the present work we show one such a case. We discuss how a mixed Kronecker Product Graph Model can be represented as a BN, and study its BN properties that can be used for efficient sampling. Specifically, we show that instead of exhibiting CSI properties, the model has deterministic context-specific dependence (DCSD). Exploiting this property focuses the sampling method on a subset of the sampling space that improves efficiency.

Dynamic networks, also called network streams, are an important data representation that applies to many real-world domains. Many sets of network data such as e-mail networks, social networks, or internet traffic networks are best represented by a dynamic network due to the temporal component of the data. One important application in the domain of dynamic network analysis is anomaly detection. Here the task is to identify points in time where the network exhibits behavior radically different from a typical time, either due to some event (like the failure of machines in a computer network) or a shift in the network properties. This problem is made more difficult by the fluid nature of what is considered "normal" network behavior. The volume of traffic on a network, for example, can change over the course of a month or even vary based on the time of the day without being considered unusual. Anomaly detection tests using traditional network statistics have difficulty in these scenarios due to their Density Dependence: as the volume of edges changes the value of the statistics changes as well making it difficult to determine if the change in signal is due to the traffic volume or due to some fundamental shift in the behavior of the network. To more accurately detect anomalies in dynamic networks, we introduce the concept of Density-Consistent network statistics. On synthetically generated graphs anomaly detectors using these statistics show a a 20-400% improvement in the recall when distinguishing graphs drawn from different distributions. When applied to several real datasets Density-Consistent statistics recover multiple network events which standard statistics failed to find.

From social networks to Internet applications, a wide variety of electronic communication tools are producing streams of graph data; where the nodes represent users and the edges represent the contacts between them over time. This has led to an increased interest in mechanisms to model the dynamic structure of time-varying graphs. In this work, we develop a framework for learning the latent state space of a time-varying email graph. We show how the framework can be used to find subsequences that correspond to global real-time events in the Email graph (e.g. vacations, breaks, ...etc.). These events impact the underlying graph process to make its characteristics non-stationary. Within the framework, we compare two different representations of the temporal relationships; discrete vs. probabilistic. We use the two representations as inputs to a mixture model to learn the latent state transitions that correspond to important changes in the Email graph structure over time.

A key challenge within the social network literature is the problem of network generation - that is, how can we create synthetic networks that match characteristics traditionally found in most real world networks? Important characteristics that are present in social networks include a power law degree distribution, small diameter and large amounts of clustering; however, most current network generators, such as the Chung Lu and Kronecker models, largely ignore the clustering present in a graph and choose to focus on preserving other network statistics, such as the power law distribution. Models such as the exponential random graph model have a transitivity parameter, but are computationally difficult to learn, making scaling to large real world networks intractable. In this work, we propose an extension to the Chung Lu ran- dom graph model, the Transitive Chung Lu (TCL) model, which incorporates the notion of a random transitive edge. That is, with some probability it will choose to connect to a node exactly two hops away, having been introduced to a 'friend of a friend'. In all other cases it will follow the standard Chung Lu model, selecting a 'random surfer' from anywhere in the graph according to the given invariant distribution. We prove TCL's expected degree distribution is equal to the degree distribution of the original graph, while being able to capture the clustering present in the network. The single parameter required by our model can be learned in seconds on graphs with millions of edges, while networks can be generated in time that is linear in the number of edges. We demonstrate the performance TCL on four real- world social networks, including an email dataset with hundreds of thousands of nodes and millions of edges, showing TCL generates graphs that match the degree distribution, clustering coefficients and hop plots of the original networks., 11 pages

The majority of real-world networks are dynamic and extremely large (e.g., Internet Traffic, Twitter, Facebook, ...). To understand the structural behavior of nodes in these large dynamic networks, it may be necessary to model the dynamics of behavioral roles representing the main connectivity patterns over time. In this paper, we propose a dynamic behavioral mixed-membership model (DBMM) that captures the roles of nodes in the graph and how they evolve over time. Unlike other node-centric models, our model is scalable for analyzing large dynamic networks. In addition, DBMM is flexible, parameter-free, has no functional form or parameterization, and is interpretable (identifies explainable patterns). The performance results indicate our approach can be applied to very large networks while the experimental results show that our model uncovers interesting patterns underlying the dynamics of these networks.

Relational data representations have become an increasingly important topic due to the recent proliferation of network datasets (e.g., social, biological, information networks) and a corresponding increase in the application of statistical relational learning (SRL) algorithms to these domains. In this article, we examine a range of representation issues for graph-based relational data. Since the choice of relational data representation for the nodes, links, and features can dramatically affect the capabilities of SRL algorithms, we survey approaches and opportunities for relational representation transformation designed to improve the performance of these algorithms. This leads us to introduce an intuitive taxonomy for data representation transformations in relational domains that incorporates link transformation and node transformation as symmetric representation tasks. In particular, the transformation tasks for both nodes and links include (i) predicting their existence, (ii) predicting their label or type, (iii) estimating their weight or importance, and (iv) systematically constructing their relevant features. We motivate our taxonomy through detailed examples and use it to survey and compare competing approaches for each of these tasks. We also discuss general conditions for transforming links, nodes, and features. Finally, we highlight challenges that remain to be addressed.

Much of the past work in network analysis has focused on analyzing discrete graphs, where binary edges represent the "presence" or "absence" of a relationship. Since traditional network measures (e.g., betweenness centrality) utilize a discrete link structure, complex systems must be transformed to this representation in order to investigate network properties. However, in many domains there may be uncertainty about the relationship structure and any uncertainty information would be lost in translation to a discrete representation. Uncertainty may arise in domains where there is moderating link information that cannot be easily observed, i.e., links become inactive over time but may not be dropped or observed links may not always corresponds to a valid relationship. In order to represent and reason with these types of uncertainty, we move beyond the discrete graph framework and develop social network measures based on a probabilistic graph representation. More specifically, we develop measures of path length, betweenness centrality, and clustering coefficient---one set based on sampling and one based on probabilistic paths. We evaluate our methods on three real-world networks from Enron, Facebook, and DBLP, showing that our proposed methods more accurately capture salient effects without being susceptible to local noise, and that the resulting analysis produces a better understanding of the graph structure and the uncertainty resulting from its change over time., Longer version of paper appearing in Fifth International AAAI Conference on Weblogs and Social Media. 9 pages, 4 Figures

Temporal networks are ubiquitous and evolve over time by the addition, deletion, and changing of links, nodes, and attributes. Although many relational datasets contain temporal information, the majority of existing techniques in relational learning focus on static snapshots and ignore the temporal dynamics. We propose a framework for discovering temporal representations of relational data to increase the accuracy of statistical relational learning algorithms. The temporal relational representations serve as a basis for classification, ensembles, and pattern mining in evolving domains. The framework includes (1) selecting the time-varying relational components (links, attributes, nodes), (2) selecting the temporal granularity, (3) predicting the temporal influence of each time-varying relational component, and (4) choosing the weighted relational classifier. Additionally, we propose temporal ensemble methods that exploit the temporal-dimension of relational data. These ensembles outperform traditional and more sophisticated relational ensembles while avoiding the issue of learning the most optimal representation. Finally, the space of temporal-relational models are evaluated using a sample of classifiers. In all cases, the proposed temporal-relational classifiers outperform competing models that ignore the temporal information. The results demonstrate the capability and necessity of the temporal-relational representations for classification, ensembles, and for mining temporal datasets.