As more practical and scalable quantum computers emerge, much attention has been focused on realizing quantum supremacy in machine learning. Existing quantum ML methods either (1) embed a classical model into a target Hamiltonian to enable quantum optimization or (2) represent a quantum model using variational quantum circuits and apply classical gradient-based optimization. The former method leverages the power of quantum optimization but only supports simple ML models, while the latter provides flexibility in model design but relies on gradient calculation, resulting in barren plateau (i.e., gradient vanishing) and frequent classical-quantum interactions. To address the limitations of existing quantum ML methods, we introduce Quark, a gradient-free quantum learning framework that optimizes quantum ML models using quantum optimization. Quark does not rely on gradient computation and therefore avoids barren plateau and frequent classical-quantum interactions. In addition, Quark can support more general ML models than prior quantum ML methods and achieves a dataset-size-independent optimization complexity. Theoretically, we prove that Quark can outperform classical gradient-based methods by reducing model query complexity for highly non-convex problems; empirically, evaluations on the Edge Detection and Tiny-MNIST tasks show that Quark can support complex ML models and significantly reduce the number of measurements needed for discovering near-optimal weights for these tasks.
Boosting the runtime performance of deep neural networks (DNNs) is critical due to their wide adoption in real-world tasks. Existing approaches to optimizing the tensor algebra expression of a DNN only consider expressions representable by a fixed set of predefined operators, missing possible optimization opportunities between general expressions. We propose OLLIE, the first derivation-based tensor program optimizer. OLLIE optimizes tensor programs by leveraging transformations between general tensor algebra expressions, enabling a significantly larger expression search space that includes those supported by prior work as special cases. OLLIE uses a hybrid derivation-based optimizer that effectively combines explorative and guided derivations to quickly discover highly optimized expressions. Evaluation on seven DNNs shows that OLLIE can outperform existing optimizers by up to 2.73$\times$ (1.46$\times$ on average) on an A100 GPU and up to 2.68$\times$ (1.51$\times$) on a V100 GPU, respectively.
Graph outlier detection is an emerging but crucial machine learning task with numerous applications. Despite the proliferation of algorithms developed in recent years, the lack of a standard and unified setting for performance evaluation limits their advancement and usage in real-world applications. To tap the gap, we present, (to our best knowledge) the first comprehensive unsupervised node outlier detection benchmark for graphs called UNOD, with the following highlights: (1) evaluating fourteen methods with backbone spanning from classical matrix factorization to the latest graph neural networks; (2) benchmarking the method performance with different types of injected outliers and organic outliers on real-world datasets; (3) comparing the efficiency and scalability of the algorithms by runtime and GPU memory usage on synthetic graphs at different scales. Based on the analyses of extensive experimental results, we discuss the pros and cons of current UNOD methods, and point out multiple crucial and promising future research directions.
The Mixture of Experts architecture allows for outrageously large neural networks by scaling model parameter size independently from computational demand (FLOPs). However, current DNN frameworks cannot effectively support the dynamic data flow in Mixture of Experts, and implementations on top of these frameworks need to use workarounds that introduce significant overheads. To address the limitation of these frameworks, we present DynaMoE, a DNN library that uses dynamic recompilations to optimize and adapt the use of computational resources to the dynamic needs of Mixture of Experts models. Our evaluation shows that DynaMoE achieves a 1.8x speedup and supports 2.3x larger model sizes when compared to existing MoE systems, even when not using recompilations. We then present further optimizations enabled by dynamic recompilations that yield an additional 1.7x speedup while simultaneously reducing memory pressure and improving model quality.
PyGOD is an open-source Python library for detecting outliers on graph data. As the first comprehensive library of its kind, PyGOD supports a wide array of leading graph-based methods for node-, edge-, subgraph-, and graph-level outlier detection, under a unified, well-documented API designed for use by both researchers and practitioners. To overcome the scalability issue in large graphs, we provide advanced functionalities for selected models, including mini-batch and sampling. PyGOD is equipped with best practices to foster code reliability and maintainability, including unit testing, continuous integration, and code coverage. To foster accessibility, PyGOD is released under a permissive BSD-license at https://github.com/pygod-team/pygod/ and the Python Package Index (PyPI).
DNN models across many domains continue to grow in size, resulting in high resource requirements for effective training, and unpalatable (and often unaffordable) costs for organizations and research labs across scales. This paper aims to significantly reduce training costs with effective use of preemptible instances, i.e., those that can be obtained at a much cheaper price while idle, but may be preempted whenever requested by priority users. Doing so, however, requires new forms of resiliency and efficiency to cope with the possibility of frequent preemptions - a failure model that is drastically different from the occasional failures in normal cluster settings that existing checkpointing techniques target. We present Bamboo, a distributed system that tackles these challenges by introducing redundant computations into the training pipeline, i.e., whereby one node performs computations over not only its own layers but also over some layers in its neighbor. Our key insight is that training large models often requires pipeline parallelism where "pipeline bubbles" naturally exist. Bamboo carefully fills redundant computations into these bubbles, providing resilience at a low cost. Across a variety of widely used DNN models, Bamboo outperforms traditional checkpointing by 3.7x in training throughput, and reduces costs by 2.4x compared to a setting where on-demand instances are used.
Strong demands for efficient deployment of Deep Learning (DL) applications prompt the rapid development of a rich DL ecosystem. To keep up with its fast advancement, it is crucial for DL frameworks to efficiently integrate a variety of optimized libraries and runtimes as their backends and generate the fastest possible executable by using them properly. However, current DL frameworks require significant manual effort to integrate diverse backends and often fail to deliver high performance. In this paper, we propose Collage, an automatic framework for integrating DL backends. Collage provides a backend registration interface that allows users to precisely specify the capability of various backends. By leveraging the specifications of available backends, Collage searches for an optimized backend placement for a given workload and execution environment. Our evaluation shows that Collage automatically integrates multiple backends together without manual intervention, and outperforms existing frameworks by 1.21x, 1.39x, 1.40x on two different NVIDIA GPUs and an Intel CPU respectively.
To scale outlier detection (OD) to large-scale, high-dimensional datasets, we propose TOD, a novel system that abstracts OD algorithms into basic tensor operations for efficient GPU acceleration. To make TOD highly efficient in both time and space, we leverage recent advances in deep learning infrastructure in both hardware and software. To deploy large OD applications on GPUs with limited memory, we introduce two key techniques. First, provable quantization accelerates OD computation and reduces the memory requirement by performing specific OD computations in lower precision while provably guaranteeing no accuracy loss. Second, to exploit the aggregated compute resources and memory capacity of multiple GPUs, we introduce automatic batching, which decomposes OD computations into small batches that can be executed on multiple GPUs in parallel. TOD supports a comprehensive set of OD algorithms and utility functions. Extensive evaluation on both real and synthetic OD datasets shows that TOD is on average 11.9X faster than the state-of-the-art comprehensive OD system PyOD, and takes less than an hour to detect outliers within a million samples. TOD enables straightforward integration for additional OD algorithms and provides a unified framework for combining classical OD algorithms with deep learning methods. These combinations result in an infinite number of OD methods, many of which are novel and can be easily prototyped in TOD.
A key challenge in neural architecture search (NAS) is quickly inferring the predictive performance of a broad spectrum of networks to discover statistically accurate and computationally efficient ones. We refer to this task as model performance inference (MPI). The current practice for efficient MPI is gradient-based methods that leverage the gradients of a network at initialization to infer its performance. However, existing gradient-based methods rely only on heuristic metrics and lack the necessary theoretical foundations to consolidate their designs. We propose GradSign, an accurate, simple, and flexible metric for model performance inference with theoretical insights. The key idea behind GradSign is a quantity {\Psi} to analyze the optimization landscape of different networks at the granularity of individual training samples. Theoretically, we show that both the network's training and true population losses are proportionally upper-bounded by {\Psi} under reasonable assumptions. In addition, we design GradSign, an accurate and simple approximation of {\Psi} using the gradients of a network evaluated at a random initialization state. Evaluation on seven NAS benchmarks across three training datasets shows that GradSign generalizes well to real-world networks and consistently outperforms state-of-the-art gradient-based methods for MPI evaluated by Spearman's {\rho} and Kendall's Tau. Additionally, we integrate GradSign into four existing NAS algorithms and show that the GradSign-assisted NAS algorithms outperform their vanilla counterparts by improving the accuracies of best-discovered networks by up to 0.3%, 1.1%, and 1.0% on three real-world tasks.
A graph neural network (GNN) enables deep learning on structured graph data. There are two major GNN training obstacles: 1) it relies on high-end servers with many GPUs which are expensive to purchase and maintain, and 2) limited memory on GPUs cannot scale to today's billion-edge graphs. This paper presents Dorylus: a distributed system for training GNNs. Uniquely, Dorylus can take advantage of serverless computing to increase scalability at a low cost. The key insight guiding our design is computation separation. Computation separation makes it possible to construct a deep, bounded-asynchronous pipeline where graph and tensor parallel tasks can fully overlap, effectively hiding the network latency incurred by Lambdas. With the help of thousands of Lambda threads, Dorylus scales GNN training to billion-edge graphs. Currently, for large graphs, CPU servers offer the best performance-per-dollar over GPU servers. Just using Lambdas on top of CPU servers offers up to 2.75x more performance-per-dollar than training only with CPU servers. Concretely, Dorylus is 1.22x faster and 4.83x cheaper than GPU servers for massive sparse graphs. Dorylus is up to 3.8x faster and 10.7x cheaper compared to existing sampling-based systems.