More Like this

1. streamingRPHash: Random Projection Clustering of High-Dimensional Data in a MapReduce Framework

   https://doi.org/10.1109/CLUSTER.2016.89  

   Franklin, Jacob ; Wenke, Samuel ; Quasem, Sadiq ; Carraher, Lee A. ; Wilsey, Philip A. ( September 2016 , IEEE Cluster 2016)

   The size and amount of data captured from numerous sources has created a situation where the large quantity of data challenges our ability to understand the meaning within the data. This has motivated studies for mechanized data analysis and in particular for the clustering, or partitioning, of data into related groups. In fact, the size of the data has grown to the point where it is now often necessary to stream the data through the system for online and high speed analysis. This paper explores the application of approximate methods for the stream clustering of high-dimensional data (feature sizes contains 100+ measures). In particular, the algorithm that has been developed, called streamingRPHash, combines Random Projection with Locality Sensitive Hashing and a count-min sketch to implement a high-performance method for the parallel and distributed clustering of streaming data in a MapReduce framework. streamingRPHash is able to perform clustering at a rate much faster than traditional clustering algorithms such as K-Means. streamingRPHash provides clustering results that are only slightly less accurate than K-Means, but in runtimes that are nearly half that required by K-Means. The performance advantage for streamingRPHash becomes even more significant as the dimensionality of the input data stream increases.more »Furthermore, the experimental results show that streamingRPHash has a near linear speedup relative to the number of CPU cores. This speedup efficiency is possible because the approximate methods used in streamingRPHash allow independent and largely unsynchronized analyses to be performed on each streamed data vectors.« less
2. Experiences on Clustering High-Dimensional Data using pbdR

   https://doi.org/10.1145/3144763.3144768  

   Amreen, Sadika ; Mockus, Audris ( January 2017 , Proceedings of the 1st International Workshop on Software Engineering for High Performance Computing in Computational and Data-enabled Science & Engineering)

   Motivation: Software engineering for High Performace Computing (HPC) environments in general [1] and for big data in particular [5] faces a set of unique challenges including high complexity of middleware and of computing environments. Tools that make it easier for scientists to utilize HPC are, therefore, of paramount importance. We provide an experience report of using one of such highly effective middleware pbdR [9] that allow the scientist to use R programming language without, at least nominally, having to master many layers of HPC infrastructure, such as OpenMPI [4] and ScalaPACK [2]. Objective: to evaluate the extent to which middleware helps improve scientist productivity, we use pbdR to solve a real problem that we, as scientists, are investigating. Our big data comes from the commits on GitHub and other project hosting sites and we are trying to cluster developers based on the text of these commit messages. Context: We need to be able to identify developer for every commit and to identify commits for a single developer. Developer identifiers in the commits, such as login, email, and name are often spelled in multiple ways since that information may come from different version control systems (Git, Mercurial, SVN, ...) and maymore »depend on which computer is used (what is specified in .git/config of the home folder). Method: We train Doc2Vec [7] model where existing credentials are used as a document identifier and then use the resulting 200-dimensional vectors for the 2.3M identifiers to cluster these identifiers so that each cluster represents a specific individual. The distance matrix occupies 32TB and, therefore, is a good target for HPC in general and pbdR in particular. pbdR allows data to be distributed over computing nodes and even has implemented K-means and mixture-model clustering techniques in the package pmclust. Results: We used strategic prototyping [3] to evaluate the capabilities of pbdR and discovered that a) the use of middleware required extensive understanding of its inner workings thus negating many of the expected benefits; b) the implemented algorithms were not suitable for the particular combination of n, p, and k (sample size, data dimension, and the number of clusters); c) the development environment based on batch jobs increases development time substantially. Conclusions: In addition to finding from Basili et al., we find that the quality of the implementation of HPC infrastructure and its development environment has a tremendous effect on development productivity.« less
3. Coreset Clustering on Small Quantum Computers

   https://doi.org/10.3390/electronics10141690  

   Tomesh, Teague ; Gokhale, Pranav ; Anschuetz, Eric R. ; Chong, Frederic T. ( July 2021 , Electronics)

   null (Ed.)

   Many quantum algorithms for machine learning require access to classical data in superposition. However, for many natural data sets and algorithms, the overhead required to load the data set in superposition can erase any potential quantum speedup over classical algorithms. Recent work by Harrow introduces a new paradigm in hybrid quantum-classical computing to address this issue, relying on coresets to minimize the data loading overhead of quantum algorithms. We investigated using this paradigm to perform k-means clustering on near-term quantum computers, by casting it as a QAOA optimization instance over a small coreset. We used numerical simulations to compare the performance of this approach to classical k-means clustering. We were able to find data sets with which coresets work well relative to random sampling and where QAOA could potentially outperform standard k-means on a coreset. However, finding data sets where both coresets and QAOA work well—which is necessary for a quantum advantage over k-means on the entire data set—appears to be challenging.
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] 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 producemore »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. Hybrid Clustering of Single-Cell Gene Expression and Spatial Information via Integrated NMF and K-Means

   https://doi.org/10.3389/fgene.2021.763263  

   Oh, Sooyoun ; Park, Haesun ; Zhang, Xiuwei ( November 2021 , Frontiers in Genetics)

   Advances in single cell transcriptomics have allowed us to study the identity of single cells. This has led to the discovery of new cell types and high resolution tissue maps of them. Technologies that measure multiple modalities of such data add more detail, but they also complicate data integration. We offer an integrated analysis of the spatial location and gene expression profiles of cells to determine their identity. We propose scHybridNMF (single-cell Hybrid Nonnegative Matrix Factorization), which performs cell type identification by combining sparse nonnegative matrix factorization (sparse NMF) with k-means clustering to cluster high-dimensional gene expression and low-dimensional location data. We show that, under multiple scenarios, including the cases where there is a small number of genes profiled and the location data is noisy, scHybridNMF outperforms sparse NMF, k-means, and an existing method that uses a hidden Markov random field to encode cell location and gene expression data for cell type identification.