Label efficiency has become an increasingly important objective in deep learning applications. Active learning aims to reduce the number of labeled examples needed to train deep networks, but the empirical performance of active learning algorithms can vary dramatically across datasets and applications. It is difficult to know in advance which active learning strategy will perform well or best in a given application. To address this, we propose the first adaptive algorithm selection strategy for deep active learning. For any unlabeled dataset, our (meta) algorithm TAILOR (Thompson ActIve Learning algORithm selection) iteratively and adaptively chooses among a set of candidate active learning algorithms. TAILOR uses novel reward functions aimed at gathering class-balanced examples. Extensive experiments in multi-class and multi-label applications demonstrate TAILOR's effectiveness in achieving accuracy comparable or better than that of the best of the candidate algorithms. Our implementation of TAILOR is open-sourced at https://github.com/jifanz/TAILOR.

The 17th International Workshop on Mining and Learning with Graphs (MLG) is held in Washington DC, USA on August 15, 2022 and is co-located with the Eighth International Workshop on Deep Learning on Graphs (DLG) as part of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. This workshop is a forum for exchanging ideas and methods for mining and learning with graphs, developing new common understandings of the problems at hand, sharing of data sets where applicable, and leveraging existing knowledge from different disciplines. In doing so, we aim to better understand the overarching principles and the limitations of our current methods, and to inspire research on new algorithms and techniques for mining and learning with graphs. Topics of interest include, but are not limited to, graph mining, statistical relational learning, social network analysis, and network science. The target audience spans researchers and practitioners across academia, government, and industry.

The emerging 5G services offer numerous new opportunities for networked applications. In this study, we seek to answer two key questions: i) is the throughput of mmWave 5G predictable, and ii) can we build "good" machine learning models for 5G throughput prediction? To this end, we conduct a measurement study of commercial mmWave 5G services in a major U.S. city, focusing on the throughput as perceived by applications running on user equipment (UE). Through extensive experiments and statistical analysis, we identify key UE-side factors that affect 5G performance and quantify to what extent the 5G throughput can be predicted. We then propose Lumos5G -- a composable machine learning (ML) framework that judiciously considers features and their combinations, and apply state-of-the-art ML techniques for making context-aware 5G throughput predictions. We demonstrate that our framework is able to achieve 1.37X to 4.84X reduction in prediction error compared to existing models. Our work can be viewed as a feasibility study for building what we envisage as a dynamic 5G throughput map (akin to Google traffic map). We believe this approach provides opportunities and challenges in building future 5G-aware apps.

Since its inception, Facebook has become an integral part of the online social community. People rely on Facebook to connect with others and build communities. As a result, it is paramount to protect the integrity of such a large network in a fast and scalable manner. In this paper, we present our efforts to protect various social media entities at Facebook from people who try to abuse our platform. We present a novel Temporal Interaction EmbeddingS (TIES) model that is designed to capture rogue social interactions and flag them for further suitable actions. TIES is a supervised, deep learning, production ready model at Facebook-scale networks. Prior works on integrity problems are mostly focused on capturing either only static or certain dynamic features of social entities. In contrast, TIES can capture both these variant behaviors in a unified model owing to the recent strides made in the domains of graph embedding and deep sequential pattern learning. To show the real-world impact of TIES, we present a few applications especially for preventing spread of misinformation, fake account detection, and reducing ads payment risks in order to enhance Facebook platform's integrity.

Inspired by convolutional neural networks on 1D and 2D data, graph convolutional neural networks (GCNNs) have been developed for various learning tasks on graph data, and have shown superior performance on real-world datasets. Despite their success, there is a dearth of theoretical explorations of GCNN models such as their generalization properties. In this paper, we take a first step towards developing a deeper theoretical understanding of GCNN models by analyzing the stability of single-layer GCNN models and deriving their generalization guarantees in a semi-supervised graph learning setting. In particular, we show that the algorithmic stability of a GCNN model depends upon the largest absolute eigenvalue of its graph convolution filter. Moreover, to ensure the uniform stability needed to provide strong generalization guarantees, the largest absolute eigenvalue must be independent of the graph size. Our results shed new insights on the design of new & improved graph convolution filters with guaranteed algorithmic stability. We evaluate the generalization gap and stability on various real-world graph datasets and show that the empirical results indeed support our theoretical findings. To the best of our knowledge, we are the first to study stability bounds on graph learning in a semi-supervised setting and derive generalization bounds for GCNN models.

For the purpose of learning on graphs, we hunt for a graph feature representation that exhibit certain uniqueness, stability and sparsity properties while also being amenable to fast computation. This leads to the discovery of family of graph spectral distances (denoted as FGSD) and their based graph feature representations, which we prove to possess most of these desired properties. To both evaluate the quality of graph features produced by FGSD and demonstrate their utility, we apply them to the graph classification problem. Through extensive experiments, we show that a simple SVM based classification algorithm, driven with our powerful FGSD based graph features, significantly outperforms all the more sophisticated state-of-art algorithms on the unlabeled node datasets in terms of both accuracy and speed; it also yields very competitive results on the labeled datasets - despite the fact it does not utilize any node label information.

An Amplified DNS DDoS (ADD) attack involves tens of thousands of DNS resolvers that send huge volumes of amplified DNS responses to a single victim host, quickly flooding the victim's network bandwidth. Because ADD attacks are distributed, it is difficult for individual DNS resolvers to detect them based on local DNS query rates alone. Even if a victim detects an ADD attack, it cannot stop the attacker from flooding its network bandwidth. To address this problem, we present a novel mitigation system called"Distributed Rate Sharing based Amplified DNS-DDoS Attack Mitigation" (DRS-ADAM). DRS-ADAM facilitates DNS query rate sharing between DNS resolvers that are involved in an attack to detect and completely stop an ADD attack. Each DNS resolver quickly builds the global DNS query rate for potential victims by accumulating the shared rate values, and uses that global rate to make mitigation decisions locally. DRS-ADAM can be easily deployed through a small software update on resolvers and victim hosts, and does not require any additional server component. Our simulation results show that DRS-ADAM can contain the peak attack rates close to a victim's acceptable threshold values (which are far smaller than their sustainable bandwidth) at all times, regardless of the number of resolvers involved in ADD attacks. ADD attacks can be fully mitigated within a few seconds.

We conduct a detailed analysis of cellular communication patterns using (voice/text based) call detail records (CDR) dataset from a nationwide cellular network. We analyze a 5-month large dataset containing over hundreds of millions of CDRs with a user population of over 5 million to dissect meaningful communication patterns, with the goal to understand their impact on - and better manage - cellular network resources. What makes this dataset interesting is that we have both location and timestamp information of the caller and the callee. This allows us to associate communication patterns of users with geographic locations. The enormous size and diversity inherent in the (big)data set, however, makes extracting communication patterns a challenging task. We illustrate this diversity by analyzing tower-level activities and communication patterns between towers and find certain patterns emerging. However, due to the complex structure of the data, extracting them becomes non-trivial. By providing structures to the data in the form of matrices, we adopt machine learning techniques to extract "latent" patterns from the data, while accounting for the inherent non-linearity and skewed data distributions. Our main results reveal the existence of interesting regional communication patterns of varying localities and sizes, out of which one pattern scatters across the entire nation.