arXiv subjects

Minjie Wang

Publications and source records attributed to Minjie Wang.

At least 37 records · Page 2Linked to original sources

arXiv2023

GNNFlow: A Distributed Framework for Continuous Temporal GNN Learning on Dynamic Graphs

Graph Neural Networks (GNNs) play a crucial role in various fields. However, most existing deep graph learning frameworks assume pre-stored static graphs and do not support training on graph streams. In contrast, many real-world graphs are dynamic and contain time domain information. We introduce GNNFlow, a distributed framework that enables efficient continuous temporal graph representation learning on dynamic graphs on multi-GPU machines. GNNFlow introduces an adaptive time-indexed block-based data structure that effectively balances memory usage with graph update and sampling operation efficiency. It features a hybrid GPU-CPU graph data placement for rapid GPU-based temporal neighborhood sampling and kernel optimizations for enhanced sampling processes. A dynamic GPU cache for node and edge features is developed to maximize cache hit rates through reuse and restoration strategies. GNNFlow supports distributed training across multiple machines with static scheduling to ensure load balance. We implement GNNFlow based on DGL and PyTorch. Our experimental results show that GNNFlow provides up to 21.1x faster continuous learning than existing systems.

cs.DC↗

arXiv2023

Causal Discovery with Generalized Linear Models through Peeling Algorithms

This article presents a novel method for causal discovery with generalized structural equation models suited for analyzing diverse types of outcomes, including discrete, continuous, and mixed data. Causal discovery often faces challenges due to unmeasured confounders that hinder the identification of causal relationships. The proposed approach addresses this issue by developing two peeling algorithms (bottom-up and top-down) to ascertain causal relationships and valid instruments. This approach first reconstructs a super-graph to represent ancestral relationships between variables, using a peeling algorithm based on nodewise GLM regressions that exploit relationships between primary and instrumental variables. Then, it estimates parent-child effects from the ancestral relationships using another peeling algorithm while deconfounding a child's model with information borrowed from its parents' models. The article offers a theoretical analysis of the proposed approach, which establishes conditions for model identifiability and provides statistical guarantees for accurately discovering parent-child relationships via the peeling algorithms. Furthermore, the article presents numerical experiments showcasing the effectiveness of our approach in comparison to state-of-the-art structure learning methods without confounders. Lastly, it demonstrates an application to Alzheimer's disease (AD), highlighting the utility of the method in constructing gene-to-gene and gene-to-disease regulatory networks involving Single Nucleotide Polymorphisms (SNPs) for healthy and AD subjects.

stat.ME↗

arXiv2023

Proof-of-principle demonstration of temporally multiplexed quantum repeater link based on atomic ensemble

Duan-Lukin-Cirac-Zoller quantum repeater protocol provides a feasible scheme to implement long-distance quantum communication and large-scale quantum networks. The elementary link, namely the entanglement between two atomic ensembles, is a fundamental component of quantum repeater. For practical quantum repeater, it is required that the elementary link can be prepared with high yield and the spin waves stored in atoms can be efficiently converted into photons on demand. However, so far, such quantum repeater link has not been demonstrated in experiments. Here, we demonstrate a proof-of-principle multiplexed quantum repeater link by entangling two temporally multiplexed quantum memory. Compared with a single-mode link, the successful preparation rate of the multiplexed link is increased by one order of magnitude. By using the cavity-enhanced scheme, the on-demand retrieval efficiency of atomic spin waves is improved to 70%, which is beneficial for the subsequent entanglement swapping between adjacent links. The realization of temporally multiplexed quantum repeater link with high retrieval efficiency lays a foundation for the development of practical quantum networks.

quant-ph↗

arXiv2023

Cavity-enhanced and spatial-multimode spin-wave-photon quantum interface

Practical realizations of quantum repeaters require quantum memory simultaneously providing high retrieval efficiency, long lifetime and multimode storages. So far, the combination of high retrieval efficiency and spatially multiplexed storages into a single memory remains challenging. Here, we set up a ring cavity that supports an array including 6 TEM00 modes and then demonstrated cavity enhanced and spatially multiplexed spin wave photon quantum interface (QI). The cavity arrangement is according to Fermat' optical theorem, which enables the six modes to experience the same optical length per round trip. Each mode includesn horizontal and vertical polarizations. Via DLCZ process in a cold atomic ensemble, we create non classically correlated pairs of spin waves and Stokes photons in the 12 modes. The retrieved fields from the multiplexed SWs are enhanced by the cavity and the average intrinsic retrieval efficiency reaches 70% at zero delay. The storage time for the case that cross-correlation function of the multiplexed QI is beyond 2 reaches 0.6ms .

quant-ph↗

arXiv2023

Generation of highly retrievable atom photon entanglement with a millisecond lifetime via a spatially multiplexed cavity

Qubit memory that is entangled with photonic qubit is the building block for long distance quantum repeaters. Cavity enhanced and long lived spin wave photon entanglement has been demonstrated by applying dual laser beams onto optical-lattice atoms. However, owing to cross readouts by two beams, retrieval efficiency of spin wave qubit is decreased by one quarter compared to that of single mode spin wave at all storage times. Here, by coupling cold atoms to two modes of a polarization interferometer based cavity, we achieve perfect qubit retrieval in cavity enhanced and long lived atom photon entanglement. A write laser beam is applied onto cold atoms, we then create a magnetic field insensitive spin wave qubit that is entangled with the photonic qubit encoded onto two arms of the interferometer. The spin wave qubit is retrieved by a read beam, which avoids the cross readouts. Our experiment demonstrates 540μs storage time at 50% intrinsic qubit retrieval efficiency, which is 13.5 times longer than the best reported result.

quant-ph↗

arXiv2023

Fast and Accurate Graph Learning for Huge Data via Minipatch Ensembles

Gaussian graphical models provide a powerful framework for uncovering conditional dependence relationships between sets of nodes; they have found applications in a wide variety of fields including sensor and communication networks, physics, finance, and computational biology. Often, one observes data on the nodes and the task is to learn the graph structure, or perform graphical model selection. While this is a well-studied problem with many popular techniques, there are typically three major practical challenges: i) many existing algorithms become computationally intractable in huge-data settings with tens of thousands of nodes; ii) the need for separate data-driven hyperparameter tuning considerably adds to the computational burden; iii) the statistical accuracy of selected edges often deteriorates as the dimension and/or the complexity of the underlying graph structures increase. We tackle these problems by developing the novel Minipatch Graph (MPGraph) estimator. Our approach breaks up the huge graph learning problem into many smaller problems by creating an ensemble of tiny random subsets of both the observations and the nodes, termed minipatches. We then leverage recent advances that use hard thresholding to solve the latent variable graphical model problem to consistently learn the graph on each minipatch. Our approach is computationally fast, embarrassingly parallelizable, memory efficient, and has integrated stability-based hyperparamter tuning. Additionally, we prove that under weaker assumptions than that of the Graphical Lasso, our MPGraph estimator achieves graph selection consistency. We compare our approach to state-of-the-art computational approaches for Gaussian graphical model selection including the BigQUIC algorithm, and empirically demonstrate that our approach is not only more statistically accurate but also extensively faster for huge graph learning problems.

stat.ML↗

arXiv2022

DGI: Easy and Efficient Inference for GNNs

While many systems have been developed to train Graph Neural Networks (GNNs), efficient model inference and evaluation remain to be addressed. For instance, using the widely adopted node-wise approach, model evaluation can account for up to 94% of the time in the end-to-end training process due to neighbor explosion, which means that a node accesses its multi-hop neighbors. On the other hand, layer-wise inference avoids the neighbor explosion problem by conducting inference layer by layer such that the nodes only need their one-hop neighbors in each layer. However, implementing layer-wise inference requires substantial engineering efforts because users need to manually decompose a GNN model into layers for computation and split workload into batches to fit into device memory. In this paper, we develop Deep Graph Inference (DGI) -- a system for easy and efficient GNN model inference, which automatically translates the training code of a GNN model for layer-wise execution. DGI is general for various GNN models and different kinds of inference requests, and supports out-of-core execution on large graphs that cannot fit in CPU memory. Experimental results show that DGI consistently outperforms layer-wise inference across different datasets and hardware settings, and the speedup can be over 1,000x.

cs.LG↗

arXiv2022

CEP3: Community Event Prediction with Neural Point Process on Graph

Many real world applications can be formulated as event forecasting on Continuous Time Dynamic Graphs (CTDGs) where the occurrence of a timed event between two entities is represented as an edge along with its occurrence timestamp in the graphs.However, most previous works approach the problem in compromised settings, either formulating it as a link prediction task on the graph given the event time or a time prediction problem given which event will happen next. In this paper, we propose a novel model combining Graph Neural Networks and Marked Temporal Point Process (MTPP) that jointly forecasts multiple link events and their timestamps on communities over a CTDG. Moreover, to scale our model to large graphs, we factorize the jointly event prediction problem into three easier conditional probability modeling problems.To evaluate the effectiveness of our model and the rationale behind such a decomposition, we establish a set of benchmarks and evaluation metrics for this event forecasting task. Our experiments demonstrate the superior performance of our model in terms of both model accuracy and training efficiency.

cs.LG↗

arXiv2021

Generation of entanglement between a highly wave-packet-tunable photon and a spin-wave memory in cold atoms

Controls of waveforms (pulse durations) of single photons are important tasks for effectively interconnecting disparate atomic memories in hybrid quantum networks. So far, the waveform control of single photon that is entangled with an atomic memory remains unexplored. Here, we demonstrated control of waveform length of the photon that is entangled with an atomic spin-wave memory by varying light-atom interaction time in cold atoms. The Bell parameter S as a function of the duration of photon pulse is measured, which shows that violations of Bell equality can be achieved for the photon pulse in the duration range from 40 ns to 50 us, where, S=2.64+/-0.02 and S=2.26+/-0.05 for the 40-ns and 50-μs durations, respectively. The measured results show that S parameter decreases with the increase in the pulse duration. We confirm that the increase in photon noise probability per pulse with the pulse-duration is responsible for the S decrease.

quant-ph↗

arXiv2021

Generation of perfect-cavity-enhanced atom-photon entanglement with a millisecond lifetime via a spatially-multiplexed cavity

A qubit memory is the building block for quantum information. Cavity-enhanced spin-wave-photon entanglement has been achieved by applying dual-control modes. However, owing to cross readouts between the modes, the qubit retrieval efficiency is about one quarter lower than that for a single spin-wave mode at all storage times. Here, we overcome cross readouts using a multiplexed ring cavity. The cavity is embedded with a polarization interferometer, and we create a write-out photonic qubit entangled with a magnetic-field-insensitive spin-wave qubit by applying a single-mode write-laser beam to cold atoms. The spin-wave qubit is retrieved with a single-mode read-laser beam, and the quarter retrieval-efficiency loss is avoided at all storage times. Our experiment demonstrates 50% intrinsic retrieval efficiency for 540 microsecond storage time, which is 13.5 times longer than the best reported result. Importantly, our multiplexed-cavity scheme paves one road to generate perfect-cavity-enhanced and large-scale multiplexed spin-wave-photon entanglement with a long lifetime.

quant-ph↗

arXiv2021

DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs

Graph neural networks (GNN) have shown great success in learning from graph-structured data. They are widely used in various applications, such as recommendation, fraud detection, and search. In these domains, the graphs are typically large, containing hundreds of millions of nodes and several billions of edges. To tackle this challenge, we develop DistDGL, a system for training GNNs in a mini-batch fashion on a cluster of machines. DistDGL is based on the Deep Graph Library (DGL), a popular GNN development framework. DistDGL distributes the graph and its associated data (initial features and embeddings) across the machines and uses this distribution to derive a computational decomposition by following an owner-compute rule. DistDGL follows a synchronous training approach and allows ego-networks forming the mini-batches to include non-local nodes. To minimize the overheads associated with distributed computations, DistDGL uses a high-quality and light-weight min-cut graph partitioning algorithm along with multiple balancing constraints. This allows it to reduce communication overheads and statically balance the computations. It further reduces the communication by replicating halo nodes and by using sparse embedding updates. The combination of these design choices allows DistDGL to train high-quality models while achieving high parallel efficiency and memory scalability. We demonstrate our optimizations on both inductive and transductive GNN models. Our results show that DistDGL achieves linear speedup without compromising model accuracy and requires only 13 seconds to complete a training epoch for a graph with 100 million nodes and 3 billion edges on a cluster with 16 machines. DistDGL is now publicly available as part of DGL:https://github.com/dmlc/dgl/tree/master/python/dgl/distributed.

cs.LG↗

arXiv2021

Sparse Regression for Extreme Values

We study the problem of selecting features associated with extreme values in high dimensional linear regression. Normally, in linear modeling problems, the presence of abnormal extreme values or outliers is considered an anomaly which should either be removed from the data or remedied using robust regression methods. In many situations, however, the extreme values in regression modeling are not outliers but rather the signals of interest; consider traces from spiking neurons, volatility in finance, or extreme events in climate science, for example. In this paper, we propose a new method for sparse high-dimensional linear regression for extreme values which is motivated by the Subbotin, or generalized normal distribution, which we call the extreme value linear regression model. For our method, we utilize an $\ell_p$ norm loss where $p$ is an even integer greater than two; we demonstrate that this loss increases the weight on extreme values. We prove consistency and variable selection consistency for the extreme value linear regression with a Lasso penalty, which we term the Extreme Lasso, and we also analyze the theoretical impact of extreme value observations on the model parameter estimates using the concept of influence functions. Through simulation studies and a real-world data example, we show that the Extreme Lasso outperforms other methods currently used in the literature for selecting features of interest associated with extreme values in high-dimensional regression.

stat.ME↗

arXiv2021

Thresholded Graphical Lasso Adjusts for Latent Variables: Application to Functional Neural Connectivity

In neuroscience, researchers seek to uncover the connectivity of neurons from large-scale neural recordings or imaging; often people employ graphical model selection and estimation techniques for this purpose. But, existing technologies can only record from a small subset of neurons leading to a challenging problem of graph selection in the presence of extensive latent variables. Chandrasekaran et al. (2012) proposed a convex program to address this problem that poses challenges from both a computational and statistical perspective. To solve this problem, we propose an incredibly simple solution: apply a hard thresholding operator to existing graph selection methods. Conceptually simple and computationally attractive, we demonstrate that thresholding the graphical Lasso, neighborhood selection, or CLIME estimators have superior theoretical properties in terms of graph selection consistency as well as stronger empirical results than existing approaches for the latent variable graphical model problem. We also demonstrate the applicability of our approach through a neuroscience case study on calcium-imaging data to estimate functional neural connections.

stat.ML↗

arXiv2020

FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems

Graph neural networks (GNNs) are gaining increasing popularity as a promising approach to machine learning on graphs. Unlike traditional graph workloads where each vertex/edge is associated with a scalar, GNNs attach a feature tensor to each vertex/edge. This additional feature dimension, along with consequently more complex vertex- and edge-wise computations, has enormous implications on locality and parallelism, which existing graph processing systems fail to exploit. This paper proposes FeatGraph to accelerate GNN workloads by co-optimizing graph traversal and feature dimension computation. FeatGraph provides a flexible programming interface to express diverse GNN models by composing coarse-grained sparse templates with fine-grained user-defined functions (UDFs) on each vertex/edge. FeatGraph incorporates optimizations for graph traversal into the sparse templates and allows users to specify optimizations for UDFs with a feature dimension schedule (FDS). FeatGraph speeds up end-to-end GNN training and inference by up to 32x on CPU and 7x on GPU.

cs.LG↗

arXiv2020

Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks

Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs. In this paper, we present the design principles and implementation of Deep Graph Library (DGL). DGL distills the computational patterns of GNNs into a few generalized sparse tensor operations suitable for extensive parallelization. By advocating graph as the central programming abstraction, DGL can perform optimizations transparently. By cautiously adopting a framework-neutral design, DGL allows users to easily port and leverage the existing components across multiple deep learning frameworks. Our evaluation shows that DGL significantly outperforms other popular GNN-oriented frameworks in both speed and memory consumption over a variety of benchmarks and has little overhead for small scale workloads.

cs.LG↗

arXiv2020

Long-lived and multiplexed atom-photon entanglement interface with feed-forward-controlled readouts

The quantum interface (QI) that generates entanglement between photonic and spin-wave (atomic memory) qubits is a basic building block for quantum repeaters. Realizing ensemble-based repeaters in practice requires quantum memory providing long lifetime and multimode capacity. Significant progresses have been achieved on these separate goals. The remaining challenge is to combine long-lived and multimode memories into a single QI. Here, by establishing multimode, magnetic-field-insensitive and long-wavelength spin-wave storage in laser-cooled atoms that are placed inside a phase-passively-stabilized polarization interferometer, we constructed a multiplexed QI that stores up to three long-lived spin-wave qubits. Using a feed-forward-controlled system, we demonstrated that the multiplexed QI gives rise to a 3-fold increase in the atom-photon (photon-photon) entanglement-generation probability compared to single-mode QIs. The measured Bell parameter is 2.5+/-0.1 combined with a memory lifetime up to 1ms. The presented work represents a key step forward in realizing fiber-based long-distance quantum communications.

quant-ph↗

arXiv2020

Supervised Convex Clustering

Clustering has long been a popular unsupervised learning approach to identify groups of similar objects and discover patterns from unlabeled data in many applications. Yet, coming up with meaningful interpretations of the estimated clusters has often been challenging precisely due to its unsupervised nature. Meanwhile, in many real-world scenarios, there are some noisy supervising auxiliary variables, for instance, subjective diagnostic opinions, that are related to the observed heterogeneity of the unlabeled data. By leveraging information from both supervising auxiliary variables and unlabeled data, we seek to uncover more scientifically interpretable group structures that may be hidden by completely unsupervised analyses. In this work, we propose and develop a new statistical pattern discovery method named Supervised Convex Clustering (SCC) that borrows strength from both information sources and guides towards finding more interpretable patterns via a joint convex fusion penalty. We develop several extensions of SCC to integrate different types of supervising auxiliary variables, to adjust for additional covariates, and to find biclusters. We demonstrate the practical advantages of SCC through simulations and a case study on Alzheimer's Disease genomics. Specifically, we discover new candidate genes as well as new subtypes of Alzheimer's Disease that can potentially lead to better understanding of the underlying genetic mechanisms responsible for the observed heterogeneity of cognitive decline in older adults.

stat.ME↗

arXiv2019

Integrative Generalized Convex Clustering Optimization and Feature Selection for Mixed Multi-View Data

In mixed multi-view data, multiple sets of diverse features are measured on the same set of samples. By integrating all available data sources, we seek to discover common group structure among the samples that may be hidden in individualistic cluster analyses of a single data-view. While several techniques for such integrative clustering have been explored, we propose and develop a convex formalization that will inherit the strong statistical, mathematical and empirical properties of increasingly popular convex clustering methods. Specifically, our Integrative Generalized Convex Clustering Optimization (iGecco) method employs different convex distances, losses, or divergences for each of the different data views with a joint convex fusion penalty that leads to common groups. Additionally, integrating mixed multi-view data is often challenging when each data source is high-dimensional. To perform feature selection in such scenarios, we develop an adaptive shifted group-lasso penalty that selects features by shrinking them towards their loss-specific centers. Our so-called iGecco+ approach selects features from each data-view that are best for determining the groups, often leading to improved integrative clustering. To fit our model, we develop a new type of generalized multi-block ADMM algorithm using sub-problem approximations that more efficiently fits our model for big data sets. Through a series of numerical experiments and real data examples on text mining and genomics, we show that iGecco+ achieves superior empirical performance for high-dimensional mixed multi-view data.

stat.ME↗