More Like this

1. Bounds and Complexity Results for Learning Coalition-Based Interaction Functions in Networked Social Systems

   Adiga, A. ; Kuhlman, C. ; Marathe, M. ; Ravi, S. ; Rosenkranz, D. ; Stearns, R. ; Vullikanti, A. ( April 2020 , Proceedings of the AAAI Conference on Artificial Intelligence)

   Using a discrete dynamical system model for a networked social system, we consider the problem of learning a class of local interaction functions in such networks. Our focus is on learning local functions which are based on pairwise disjoint coalitions formed from the neighborhood of each node. Our work considers both active query and PAC learning models. We establish bounds on the number of queries needed to learn the local functions under both models.We also establish a complexity result regarding efficient consistent learners for such functions. Our experimental results on synthetic and real social networks demonstrate how the number ofmore »queries depends on the structure of the underlying network and number of coalitions.« less
2. Learning Coalition-Based Interactions in Networked Social Systems

   Adiga, Abhijin ; Kuhlman, Chris J. ; Marathe, Madhav V. ; Ravi, S. S. ; Rosenkrantz, Daniel J. ; Stearns, Richard E. ; Vullikanti, Anil ( April 2020 , Association for the Advancement of Artificial Intelligence Conference 2020)

   Using a discrete dynamical system model for a networked social system, we consider the problem of learning a class of local interaction functions in such networks. Our focus is on learning local functions which are based on pairwise disjoint coalitions formed from the neighborhood of each node. Our work considers both active query and PAC learning models. We establish bounds on the number of queries needed to learn the local functions under both models.We also establish a complexity result regarding efficient consistent learners for such functions. Our experimental results on synthetic and real social networks demonstrate how the number ofmore »queries depends on the structure of the underlying network and number of coalitions.« less
3. Inferring users' choice functions in networked social systems through active queries

   Adiga, A ; Kuhlman, C ; Marathe, M ; Ravi, S ; Rosenkrantz, D ; Stearns, D ( January 2018 , The 7th International Workshop on Computational Social Choice (COMSOC-2018))

   Using synchronous dynamical systems (SyDSs) as a formal model for networked social systems, we study the problem of inferring users’ choices in such systems. We observe that SyDSs with deterministic and probabilistic threshold functions as local functions can capture users’ choices in the context of contagion propagation in social networks. We use an active query mechanism where a user interacts with a system by submitting queries, and the responses to the queries are used to infer the local functions. We develop methods that provide provably efficient query sets for inferring both deterministic and probabilistic forms of threshold functions. We alsomore »present experimental results using real world social networks.« less
4. Issues in the Reproducibility of Deep Learning Results

   https://doi.org/10.1109/SPMB47826.2019.9037840  

   Jean-Paul, S. ; Elseify, T. ; Obeid, I. ; Picone, J. ( December 2019 , IEEE Signal Processing in Medicine and Biology Symposium (SPMB))

   Obeid, I. ; Selesnik, I. ; Picone, J. (Ed.)

   The Neuronix high-performance computing cluster allows us to conduct extensive machine learning experiments on big data [1]. This heterogeneous cluster uses innovative scheduling technology, Slurm [2], that manages a network of CPUs and graphics processing units (GPUs). The GPU farm consists of a variety of processors ranging from low-end consumer grade devices such as the Nvidia GTX 970 to higher-end devices such as the GeForce RTX 2080. These GPUs are essential to our research since they allow extremely compute-intensive deep learning tasks to be executed on massive data resources such as the TUH EEG Corpus [2]. We use TensorFlow [3]more »as the core machine learning library for our deep learning systems, and routinely employ multiple GPUs to accelerate the training process. Reproducible results are essential to machine learning research. Reproducibility in this context means the ability to replicate an existing experiment – performance metrics such as error rates should be identical and floating-point calculations should match closely. Three examples of ways we typically expect an experiment to be replicable are: (1) The same job run on the same processor should produce the same results each time it is run. (2) A job run on a CPU and GPU should produce identical results. (3) A job should produce comparable results if the data is presented in a different order. System optimization requires an ability to directly compare error rates for algorithms evaluated under comparable operating conditions. However, it is a difficult task to exactly reproduce the results for large, complex deep learning systems that often require more than a trillion calculations per experiment [5]. This is a fairly well-known issue and one we will explore in this poster. Researchers must be able to replicate results on a specific data set to establish the integrity of an implementation. They can then use that implementation as a baseline for comparison purposes. A lack of reproducibility makes it very difficult to debug algorithms and validate changes to the system. Equally important, since many results in deep learning research are dependent on the order in which the system is exposed to the data, the specific processors used, and even the order in which those processors are accessed, it becomes a challenging problem to compare two algorithms since each system must be individually optimized for a specific data set or processor. This is extremely time-consuming for algorithm research in which a single run often taxes a computing environment to its limits. Well-known techniques such as cross-validation [5,6] can be used to mitigate these effects, but this is also computationally expensive. These issues are further compounded by the fact that most deep learning algorithms are susceptible to the way computational noise propagates through the system. GPUs are particularly notorious for this because, in a clustered environment, it becomes more difficult to control which processors are used at various points in time. Another equally frustrating issue is that upgrades to the deep learning package, such as the transition from TensorFlow v1.9 to v1.13, can also result in large fluctuations in error rates when re-running the same experiment. Since TensorFlow is constantly updating functions to support GPU use, maintaining an historical archive of experimental results that can be used to calibrate algorithm research is quite a challenge. This makes it very difficult to optimize the system or select the best configurations. The overall impact of all of these issues described above is significant as error rates can fluctuate by as much as 25% due to these types of computational issues. Cross-validation is one technique used to mitigate this, but that is expensive since you need to do multiple runs over the data, which further taxes a computing infrastructure already running at max capacity. GPUs are preferred when training a large network since these systems train at least two orders of magnitude faster than CPUs [7]. Large-scale experiments are simply not feasible without using GPUs. However, there is a tradeoff to gain this performance. Since all our GPUs use the NVIDIA CUDA® Deep Neural Network library (cuDNN) [8], a GPU-accelerated library of primitives for deep neural networks, it adds an element of randomness into the experiment. When a GPU is used to train a network in TensorFlow, it automatically searches for a cuDNN implementation. NVIDIA’s cuDNN implementation provides algorithms that increase the performance and help the model train quicker, but they are non-deterministic algorithms [9,10]. Since our networks have many complex layers, there is no easy way to avoid this randomness. Instead of comparing each epoch, we compare the average performance of the experiment because it gives us a hint of how our model is performing per experiment, and if the changes we make are efficient. In this poster, we will discuss a variety of issues related to reproducibility and introduce ways we mitigate these effects. For example, TensorFlow uses a random number generator (RNG) which is not seeded by default. TensorFlow determines the initialization point and how certain functions execute using the RNG. The solution for this is seeding all the necessary components before training the model. This forces TensorFlow to use the same initialization point and sets how certain layers work (e.g., dropout layers). However, seeding all the RNGs will not guarantee a controlled experiment. Other variables can affect the outcome of the experiment such as training using GPUs, allowing multi-threading on CPUs, using certain layers, etc. To mitigate our problems with reproducibility, we first make sure that the data is processed in the same order during training. Therefore, we save the data from the last experiment and to make sure the newer experiment follows the same order. If we allow the data to be shuffled, it can affect the performance due to how the model was exposed to the data. We also specify the float data type to be 32-bit since Python defaults to 64-bit. We try to avoid using 64-bit precision because the numbers produced by a GPU can vary significantly depending on the GPU architecture [11-13]. Controlling precision somewhat reduces differences due to computational noise even though technically it increases the amount of computational noise. We are currently developing more advanced techniques for preserving the efficiency of our training process while also maintaining the ability to reproduce models. In our poster presentation we will demonstrate these issues using some novel visualization tools, present several examples of the extent to which these issues influence research results on electroencephalography (EEG) and digital pathology experiments and introduce new ways to manage such computational issues.« less
5. A comparison of statistical relational learning and graph neural networks for aggregate graph queries

   https://doi.org/10.1007/s10994-021-06007-5  

   Embar, Varun ; Srinivasan, Sriram ; Getoor, Lise ( June 2021 , Machine Learning)

   Statistical relational learning (SRL) and graph neural networks (GNNs) are two powerful approaches for learning and inference over graphs. Typically, they are evaluated in terms of simple metrics such as accuracy over individual node labels. Complexaggregate graph queries(AGQ) involving multiple nodes, edges, and labels are common in the graph mining community and are used to estimate important network properties such as social cohesion and influence. While graph mining algorithms support AGQs, they typically do not take into account uncertainty, or when they do, make simplifying assumptions and do not build full probabilistic models. In this paper, we examine themore »performance of SRL and GNNs on AGQs over graphs with partially observed node labels. We show that, not surprisingly, inferring the unobserved node labels as a first step and then evaluating the queries on the fully observed graph can lead to sub-optimal estimates, and that a better approach is to compute these queries as an expectation under the joint distribution. We propose a sampling framework to tractably compute the expected values of AGQs. Motivated by the analysis of subgroup cohesion in social networks, we propose a suite of AGQs that estimate the community structure in graphs. In our empirical evaluation, we show that by estimating these queries as an expectation, SRL-based approaches yield up to a 50-fold reduction in average error when compared to existing GNN-based approaches.

   « less