arXiv subjects

Baochun Li

Publications and source records attributed to Baochun Li.

At least 37 records · Page 2Linked to original sources

arXiv2022

Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning

Federated learning (FL) has increasingly been deployed, in its vertical form, among organizations to facilitate secure collaborative training over siloed data. In vertical FL (VFL), participants hold disjoint features of the same set of sample instances. Among them, only one has labels. This participant, known as the active party, initiates the training and interacts with the other participants, known as the passive parties. Despite the increasing adoption of VFL, it remains largely unknown if and how the active party can extract feature data from the passive party, especially when training deep neural network (DNN) models. This paper makes the first attempt to study the feature security problem of DNN training in VFL. We consider a DNN model partitioned between active and passive parties, where the latter only holds a subset of the input layer and exhibits some categorical features of binary values. Using a reduction from the Exact Cover problem, we prove that reconstructing those binary features is NP-hard. Through analysis, we demonstrate that, unless the feature dimension is exceedingly large, it remains feasible, both theoretically and practically, to launch a reconstruction attack with an efficient search-based algorithm that prevails over current feature protection techniques. To address this problem, we develop a novel feature protection scheme against the reconstruction attack that effectively misleads the search to some pre-specified random values. With an extensive set of experiments, we show that our protection scheme sustains the feature reconstruction attack in various VFL applications at no expense of accuracy loss.

cs.LG↗

arXiv2022

Pisces: Efficient Federated Learning via Guided Asynchronous Training

Federated learning (FL) is typically performed in a synchronous parallel manner, where the involvement of a slow client delays a training iteration. Current FL systems employ a participant selection strategy to select fast clients with quality data in each iteration. However, this is not always possible in practice, and the selection strategy often has to navigate an unpleasant trade-off between the speed and the data quality of clients. In this paper, we present Pisces, an asynchronous FL system with intelligent participant selection and model aggregation for accelerated training. To avoid incurring excessive resource cost and stale training computation, Pisces uses a novel scoring mechanism to identify suitable clients to participate in a training iteration. It also adapts the pace of model aggregation to dynamically bound the progress gap between the selected clients and the server, with a provable convergence guarantee in a smooth non-convex setting. We have implemented Pisces in an open-source FL platform called Plato, and evaluated its performance in large-scale experiments with popular vision and language models. Pisces outperforms the state-of-the-art synchronous and asynchronous schemes, accelerating the time-to-accuracy by up to 2.0x and 1.9x, respectively.

cs.DC↗

arXiv2022

OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks

This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors. Specifically, we construct a distinct generative model and design an objective function that encourages the generative model to produce causal, compact, and faithful explanations. This is achieved by isolating the causal factors in the latent space of graphs by maximizing the information flow measurements. We theoretically analyze the cause-effect relationships in the proposed causal graph, identify node attributes as confounders between graphs and GNN predictions, and circumvent such confounder effect by leveraging the backdoor adjustment formula. Our framework is compatible with any GNNs, and it does not require access to the process by which the target GNN produces its predictions. In addition, it does not rely on the linear-independence assumption of the explained features, nor require prior knowledge on the graph learning tasks. We show a proof-of-concept of OrphicX on canonical classification problems on graph data. In particular, we analyze the explanatory subgraphs obtained from explanations for molecular graphs (i.e., Mutag) and quantitatively evaluate the explanation performance with frequently occurring subgraph patterns. Empirically, we show that OrphicX can effectively identify the causal semantics for generating causal explanations, significantly outperforming its alternatives.

cs.LG↗

arXiv2022

Optimal Streaming Erasure Codes over the Three-Node Relay Network

This paper investigates low-latency streaming codes for a three-node relay network. The source transmits a sequence of messages (streaming messages) to the destination through the relay between them, where the first-hop channel from the source to the relay and the second-hop channel from the relay to the destination are subject to packet erasures. Every source message must be recovered perfectly at the destination subject to a fixed decoding delay of $T$ time slots. In any sliding window of $T+1$ time slots, we assume no more than $N_1$ and $N_2$ erasures are introduced by the first-hop channel and second-hop channel respectively. Under this channel loss assumption, we fully characterize the maximum achievable rate in terms of $T$, $N_1$ and $N_2$. The achievability is proved by using a symbol-wise decode-forward strategy where the source symbols within the same message are decoded by the relay with different delays. The converse is proved by analyzing the maximum achievable rate for each channel when the erasures in the other channel are consecutive (bursty). In addition, we show that traditional message-wise decode-forward strategies, which require the source symbols within the same message to be decoded by the relay with the same delay, are sub-optimal in general.

cs.IT↗

arXiv2022

Towards Private Learning on Decentralized Graphs with Local Differential Privacy

Many real-world networks are inherently decentralized. For example, in social networks, each user maintains a local view of a social graph, such as a list of friends and her profile. It is typical to collect these local views of social graphs and conduct graph learning tasks. However, learning over graphs can raise privacy concerns as these local views often contain sensitive information. In this paper, we seek to ensure private graph learning on a decentralized network graph. Towards this objective, we propose {\em Solitude}, a new privacy-preserving learning framework based on graph neural networks (GNNs), with formal privacy guarantees based on edge local differential privacy. The crux of {\em Solitude} is a set of new delicate mechanisms that can calibrate the introduced noise in the decentralized graph collected from the users. The principle behind the calibration is the intrinsic properties shared by many real-world graphs, such as sparsity. Unlike existing work on locally private GNNs, our new framework can simultaneously protect node feature privacy and edge privacy, and can seamlessly incorporate with any GNN with privacy-utility guarantees. Extensive experiments on benchmarking datasets show that {\em Solitude} can retain the generalization capability of the learned GNN while preserving the users' data privacy under given privacy budgets.

cs.LG↗

arXiv2021

What Should Future Wireless Network Architectures Be?

The accelerated convergence of digital and real-world lifestyles has imposed unprecedented demands on today's wireless network architectures, as it is highly desirable for such architectures to support wireless devices everywhere with high capacity and minimal signaling overhead. Conventional architectures, such as cellular architectures, are not able to satisfy these requirements simultaneously, and are thus no longer suitable for the future era. In this paper, we propose a capacity-centric (C$^2$) architecture for future wireless communication networks. It is designed based on the principles of maximizing the number of non-overlapping clusters with the average cluster capacity guaranteed to be higher than a certain threshold, and thus provides a flexible way to balance the capacity requirement against the signaling overhead. Our analytical results reveal that C$^2$ has superior generality, wherein both the cellular and the fully coordinated architectures can be viewed as its extreme cases. Simulation results show that the average capacity of C$^2$ is at least three times higher compared to that of the cellular architecture. More importantly, different from the widely adopted conventional wisdom that base-station distributions dominate architecture designs, we find that the C$^2$ architecture is independent of base-station distributions, and instead user-side information should be the focus in future wireless network architecture designs.

cs.IT↗

arXiv2021

Generative Causal Explanations for Graph Neural Networks

This paper presents Gem, a model-agnostic approach for providing interpretable explanations for any GNNs on various graph learning tasks. Specifically, we formulate the problem of providing explanations for the decisions of GNNs as a causal learning task. Then we train a causal explanation model equipped with a loss function based on Granger causality. Different from existing explainers for GNNs, Gem explains GNNs on graph-structured data from a causal perspective. It has better generalization ability as it has no requirements on the internal structure of the GNNs or prior knowledge on the graph learning tasks. In addition, Gem, once trained, can be used to explain the target GNN very quickly. Our theoretical analysis shows that several recent explainers fall into a unified framework of additive feature attribution methods. Experimental results on synthetic and real-world datasets show that Gem achieves a relative increase of the explanation accuracy by up to $30\%$ and speeds up the explanation process by up to $110\times$ as compared to its state-of-the-art alternatives.

cs.LG↗

arXiv2020

Semi-Dynamic Load Balancing: Efficient Distributed Learning in Non-Dedicated Environments

Machine learning (ML) models are increasingly trained in clusters with non-dedicated workers possessing heterogeneous resources. In such scenarios, model training efficiency can be negatively affected by stragglers -- workers that run much slower than others. Efficient model training requires eliminating such stragglers, yet for modern ML workloads, existing load balancing strategies are inefficient and even infeasible. In this paper, we propose a novel strategy called semi-dynamic load balancing to eliminate stragglers of distributed ML workloads. The key insight is that ML workers shall be load-balanced at iteration boundaries, being non-intrusive to intra-iteration execution. We develop LB-BSP based on such an insight, which is an integrated worker coordination mechanism that adapts workers' load to their instantaneous processing capabilities by right-sizing the sample batches at the synchronization barriers. We have custom-designed the batch sizing algorithm respectively for CPU and GPU clusters based on their own characteristics. LB-BSP has been implemented as a Python module for ML frameworks like TensorFlow and PyTorch. Our EC2 deployment confirms that LB-BSP is practical, effective and light-weight, and is able to accelerating distributed training by up to $54\%$.

cs.DC↗

arXiv2020

Low-Latency Network-Adaptive Error Control for Interactive Streaming

We introduce a novel network-adaptive algorithm that is suitable for alleviating network packet losses for low-latency interactive communications between a source and a destination. Our network-adaptive algorithm estimates in real-time the best parameters of a recently proposed streaming code that uses forward error correction (FEC) to correct both arbitrary and burst losses, which cause a crackling noise and undesirable jitters, respectively in audio. In particular, the destination estimates appropriate coding parameters based on its observed packet loss pattern and sends them back to the source for updating the underlying code. Besides, a new explicit construction of practical low-latency streaming codes that achieve the optimal tradeoff between the capability of correcting arbitrary losses and the capability of correcting burst losses is provided. Simulation evaluations based on statistical losses and real-world packet loss traces reveal the following: (i) Our proposed network-adaptive algorithm combined with our optimal streaming codes can achieve significantly higher performance compared to uncoded and non-adaptive FEC schemes over UDP (User Datagram Protocol); (ii) Our explicit streaming codes can significantly outperform traditional MDS (maximum-distance separable) streaming schemes when they are used along with our network-adaptive algorithm.

cs.NI↗

arXiv2020

Towards Assessment of Randomized Smoothing Mechanisms for Certifying Adversarial Robustness

As a certified defensive technique, randomized smoothing has received considerable attention due to its scalability to large datasets and neural networks. However, several important questions remain unanswered, such as (i) whether the Gaussian mechanism is an appropriate option for certifying $\ell_2$-norm robustness, and (ii) whether there is an appropriate randomized (smoothing) mechanism to certify $\ell_\infty$-norm robustness. To shed light on these questions, we argue that the main difficulty is how to assess the appropriateness of each randomized mechanism. In this paper, we propose a generic framework that connects the existing frameworks in \cite{lecuyer2018certified, li2019certified}, to assess randomized mechanisms. Under our framework, for a randomized mechanism that can certify a certain extent of robustness, we define the magnitude of its required additive noise as the metric for assessing its appropriateness. We also prove lower bounds on this metric for the $\ell_2$-norm and $\ell_\infty$-norm cases as the criteria for assessment. Based on our framework, we assess the Gaussian and Exponential mechanisms by comparing the magnitude of additive noise required by these mechanisms and the lower bounds (criteria). We first conclude that the Gaussian mechanism is indeed an appropriate option to certify $\ell_2$-norm robustness. Surprisingly, we show that the Gaussian mechanism is also an appropriate option for certifying $\ell_\infty$-norm robustness, instead of the Exponential mechanism. Finally, we generalize our framework to $\ell_p$-norm for any $p\geq2$. Our theoretical findings are verified by evaluations on CIFAR10 and ImageNet.

cs.LG↗

arXiv2020

Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition

Skeleton-based action recognition has attracted increasing attention due to its strong adaptability to dynamic circumstances and potential for broad applications such as autonomous and anonymous surveillance. With the help of deep learning techniques, it has also witnessed substantial progress and currently achieved around 90\% accuracy in benign environment. On the other hand, research on the vulnerability of skeleton-based action recognition under different adversarial settings remains scant, which may raise security concerns about deploying such techniques into real-world systems. However, filling this research gap is challenging due to the unique physical constraints of skeletons and human actions. In this paper, we attempt to conduct a thorough study towards understanding the adversarial vulnerability of skeleton-based action recognition. We first formulate generation of adversarial skeleton actions as a constrained optimization problem by representing or approximating the physiological and physical constraints with mathematical formulations. Since the primal optimization problem with equality constraints is intractable, we propose to solve it by optimizing its unconstrained dual problem using ADMM. We then specify an efficient plug-in defense, inspired by recent theories and empirical observations, against the adversarial skeleton actions. Extensive evaluations demonstrate the effectiveness of the attack and defense method under different settings.

cs.CV↗

arXiv2020

Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled Data

Graph-based semi-supervised learning has been shown to be one of the most effective approaches for classification tasks from a wide range of domains, such as image classification and text classification, as they can exploit the connectivity patterns between labeled and unlabeled samples to improve learning performance. In this work, we advance this effective learning paradigm towards a scenario where labeled data are severely limited. More specifically, we address the problem of graph-based semi-supervised learning in the presence of severely limited labeled samples, and propose a new framework, called {\em Shoestring}, that improves the learning performance through semantic transfer from these very few labeled samples to large numbers of unlabeled samples. In particular, our framework learns a metric space in which classification can be performed by computing the similarity to centroid embedding of each class. {\em Shoestring} is trained in an end-to-end fashion to learn to leverage the semantic knowledge of limited labeled samples as well as their connectivity patterns with large numbers of unlabeled samples simultaneously. By combining {\em Shoestring} with graph convolutional networks, label propagation and their recent label-efficient variations (IGCN and GLP), we are able to achieve state-of-the-art node classification performance in the presence of very few labeled samples. In addition, we demonstrate the effectiveness of our framework on image classification tasks in the few-shot learning regime, with significant gains on miniImageNet ($2.57\%\sim3.59\%$) and tieredImageNet ($1.05\%\sim2.70\%$).

cs.CV↗

arXiv2019

Optimal Multiplexed Erasure Codes for Streaming Messages with Different Decoding Delays

This paper considers multiplexing two sequences of messages with two different decoding delays over a packet erasure channel. In each time slot, the source constructs a packet based on the current and previous messages and transmits the packet, which may be erased when the packet travels from the source to the destination. The destination must perfectly recover every source message in the first sequence subject to a decoding delay $T_\mathrm{v}$ and every source message in the second sequence subject to a shorter decoding delay $T_\mathrm{u}\le T_\mathrm{v}$. We assume that the channel loss model introduces a burst erasure of a fixed length $B$ on the discrete timeline. Under this channel loss assumption, the capacity region for the case where $T_\mathrm{v}\le T_\mathrm{u}+B$ was previously solved. In this paper, we fully characterize the capacity region for the remaining case $T_\mathrm{v}> T_\mathrm{u}+B$. The key step in the achievability proof is achieving the non-trivial corner point of the capacity region through using a multiplexed streaming code constructed by superimposing two single-stream codes. The main idea in the converse proof is obtaining a genie-aided bound when the channel is subject to a periodic erasure pattern where each period consists of a length-$B$ burst erasure followed by a length-$T_\mathrm{u}$ noiseless duration.

cs.IT↗

arXiv2018

Optimal Streaming Codes for Channels with Burst and Arbitrary Erasures

This paper considers transmitting a sequence of messages (a streaming source) over a packet erasure channel. In each time slot, the source constructs a packet based on the current and the previous messages and transmits the packet, which may be erased when the packet travels from the source to the destination. Every source message must be recovered perfectly at the destination subject to a fixed decoding delay. We assume that the channel loss model introduces either one burst erasure or multiple arbitrary erasures in any fixed-sized sliding window. Under this channel loss assumption, we fully characterize the maximum achievable rate by constructing streaming codes that achieve the optimal rate. In addition, our construction of optimal streaming codes implies the full characterization of the maximum achievable rate for convolutional codes with any given column distance, column span and decoding delay. Numerical results demonstrate that the optimal streaming codes outperform existing streaming codes of comparable complexity over some instances of the Gilbert-Elliott channel and the Fritchman channel.

cs.IT↗

arXiv2016

An Alternating Direction Method Approach to Cloud Traffic Management

In this paper, we introduce a unified framework for studying various cloud traffic management problems, ranging from geographical load balancing to backbone traffic engineering. We first abstract these real-world problems as a multi-facility resource allocation problem, and then present two distributed optimization algorithms by exploiting the special structure of the problem. Our algorithms are inspired by Alternating Direction Method of Multipliers (ADMM), enjoying a number of unique features. Compared to dual decomposition, they converge with non-strictly convex objective functions; compared to other ADMM-type algorithms, they not only achieve faster convergence under weaker assumptions, but also have lower computational complexity and lower message-passing overhead. The simulation results not only confirm these desirable features of our algorithms, but also highlight several additional advantages, such as scalability and fault-tolerance.

cs.NI↗

arXiv2015

Dispersing Instant Social Video Service Across Multiple Clouds

Instant social video sharing which combines the online social network and user-generated short video streaming services, has become popular in today's Internet. Cloud-based hosting of such instant social video contents has become a norm to serve the increasing users with user-generated contents. A fundamental problem of cloud-based social video sharing service is that users are located globally, who cannot be served with good service quality with a single cloud provider. In this paper, we investigate the feasibility of dispersing instant social video contents to multiple cloud providers. The challenge is that inter-cloud social \emph{propagation} is indispensable with such multi-cloud social video hosting, yet such inter-cloud traffic incurs substantial operational cost. We analyze and formulate the multi-cloud hosting of an instant social video system as an optimization problem. We conduct large-scale measurement studies to show the characteristics of instant social video deployment, and demonstrate the trade-off between satisfying users with their ideal cloud providers, and reducing the inter-cloud data propagation. Our measurement insights of the social propagation allow us to propose a heuristic algorithm with acceptable complexity to solve the optimization problem, by partitioning a propagation-weighted social graph in two phases: a preference-aware initial cloud provider selection and a propagation-aware re-hosting. Our simulation experiments driven by real-world social network traces show the superiority of our design.

cs.NI↗

arXiv2013

Reducing Electricity Demand Charge for Data Centers with Partial Execution

Data centers consume a large amount of energy and incur substantial electricity cost. In this paper, we study the familiar problem of reducing data center energy cost with two new perspectives. First, we find, through an empirical study of contracts from electric utilities powering Google data centers, that demand charge per kW for the maximum power used is a major component of the total cost. Second, many services such as Web search tolerate partial execution of the requests because the response quality is a concave function of processing time. Data from Microsoft Bing search engine confirms this observation. We propose a simple idea of using partial execution to reduce the peak power demand and energy cost of data centers. We systematically study the problem of scheduling partial execution with stringent SLAs on response quality. For a single data center, we derive an optimal algorithm to solve the workload scheduling problem. In the case of multiple geo-distributed data centers, the demand of each data center is controlled by the request routing algorithm, which makes the problem much more involved. We decouple the two aspects, and develop a distributed optimization algorithm to solve the large-scale request routing problem. Trace-driven simulations show that partial execution reduces cost by $3\%--10.5\%$ for one data center, and by $15.5\%$ for geo-distributed data centers together with request routing.

cs.NI↗

arXiv2013

RepFlow: Minimizing Flow Completion Times with Replicated Flows in Data Centers

Short TCP flows that are critical for many interactive applications in data centers are plagued by large flows and head-of-line blocking in switches. Hash-based load balancing schemes such as ECMP aggravate the matter and result in long-tailed flow completion times (FCT). Previous work on reducing FCT usually requires custom switch hardware and/or protocol changes. We propose RepFlow, a simple yet practically effective approach that replicates each short flow to reduce the completion times, without any change to switches or host kernels. With ECMP the original and replicated flows traverse distinct paths with different congestion levels, thereby reducing the probability of having long queueing delay. We develop a simple analytical model to demonstrate the potential improvement of RepFlow. Extensive NS-3 simulations and Mininet implementation show that RepFlow provides 50%--70% speedup in both mean and 99-th percentile FCT for all loads, and offers near-optimal FCT when used with DCTCP.

cs.NI↗