Modern smartwatches often include photoplethysmographic (PPG) sensors to measure heartbeats or blood pressure through complex algorithms that fuse PPG data with other signals. In this work, we propose a collaborative inference approach that uses both a smartwatch and a connected smartphone to maximize the performance of heart rate (HR) tracking while also maximizing the smartwatch's battery life. In particular, we first analyze the trade-offs between running on-device HR tracking or offloading the work to the mobile. Then, thanks to an additional step to evaluate the difficulty of the upcoming HR prediction, we demonstrate that we can smartly manage the workload between smartwatch and smartphone, maintaining a low mean absolute error (MAE) while reducing energy consumption. We benchmark our approach on a custom smartwatch prototype, including the STM32WB55 MCU and Bluetooth Low-Energy (BLE) communication, and a Raspberry Pi3 as a proxy for the smartphone. With our Collaborative Heart Rate Inference System (CHRIS), we obtain a set of Pareto-optimal configurations demonstrating the same MAE as State-of-Art (SoA) algorithms while consuming less energy. For instance, we can achieve approximately the same MAE of TimePPG-Small (5.54 BPM MAE vs. 5.60 BPM MAE) while reducing the energy by 2.03x, with a configuration that offloads 80\% of the predictions to the phone. Furthermore, accepting a performance degradation to 7.16 BPM of MAE, we can achieve an energy consumption of 179 uJ per prediction, 3.03x less than running TimePPG-Small on the smartwatch, and 1.82x less than streaming all the input data to the phone.
Due to limited resources on edge and different characteristics of deep neural network (DNN) models, it is a big challenge to optimize DNN inference performance in terms of energy consumption and end-to-end latency on edge devices. In addition to the dynamic voltage frequency scaling (DVFS) technique, the edge-cloud architecture provides a collaborative approach for efficient DNN inference. However, current edge-cloud collaborative inference methods have not optimized various compute resources on edge devices. Thus, we propose DVFO, a novel DVFS-enabled edge-cloud collaborative inference framework, which co-optimizes DVFS and offloading parameters via deep reinforcement learning (DRL). Specifically, DVFO automatically co-optimizes 1) the CPU, GPU and memory frequencies of edge devices, and 2) the feature maps to be offloaded to cloud servers. In addition, it leverages a thinking-while-moving concurrent mechanism to accelerate the DRL learning process, and a spatial-channel attention mechanism to extract DNN feature maps of secondary importance for workload offloading. This approach improves inference performance for different DNN models under various edge-cloud network conditions. Extensive evaluations using two datasets and six widely-deployed DNN models on three heterogeneous edge devices show that DVFO significantly reduces the energy consumption by 33% on average, compared to state-of-the-art schemes. Moreover, DVFO achieves up to 28.6%-59.1% end-to-end latency reduction, while maintaining accuracy within 1% loss on average.
Quantum processing units (QPUs) are currently exclusively available from cloud vendors. However, with recent advancements, hosting QPUs is soon possible everywhere. Existing work has yet to draw from research in edge computing to explore systems exploiting mobile QPUs, or how hybrid applications can benefit from distributed heterogeneous resources. Hence, this work presents an architecture for Quantum Computing in the edge-cloud continuum. We discuss the necessity, challenges, and solution approaches for extending existing work on classical edge computing to integrate QPUs. We describe how warm-starting allows defining workflows that exploit the hierarchical resources spread across the continuum. Then, we introduce a distributed inference engine with hybrid classical-quantum neural networks (QNNs) to aid system designers in accommodating applications with complex requirements that incur the highest degree of heterogeneity. We propose solutions focusing on classical layer partitioning and quantum circuit cutting to demonstrate the potential of utilizing classical and quantum computation across the continuum. To evaluate the importance and feasibility of our vision, we provide a proof of concept that exemplifies how extending a classical partition method to integrate quantum circuits can improve the solution quality. Specifically, we implement a split neural network with optional hybrid QNN predictors. Our results show that extending classical methods with QNNs is viable and promising for future work.
The deployment flexibility and maneuverability of Unmanned Aerial Vehicles (UAVs) increased their adoption in various applications, such as wildfire tracking, border monitoring, etc. In many critical applications, UAVs capture images and other sensory data and then send the captured data to remote servers for inference and data processing tasks. However, this approach is not always practical in real-time applications due to the connection instability, limited bandwidth, and end-to-end latency. One promising solution is to divide the inference requests into multiple parts (layers or segments), with each part being executed in a different UAV based on the available resources. Furthermore, some applications require the UAVs to traverse certain areas and capture incidents; thus, planning their paths becomes critical particularly, to reduce the latency of making the collaborative inference process. Specifically, planning the UAVs trajectory can reduce the data transmission latency by communicating with devices in the same proximity while mitigating the transmission interference. This work aims to design a model for distributed collaborative inference requests and path planning in a UAV swarm while respecting the resource constraints due to the computational load and memory usage of the inference requests. The model is formulated as an optimization problem and aims to minimize latency. The formulated problem is NP-hard so finding the optimal solution is quite complex; thus, this paper introduces a real-time and dynamic solution for online applications using deep reinforcement learning. We conduct extensive simulations and compare our results to the-state-of-the-art studies demonstrating that our model outperforms the competing models.
The cost efficiency of model inference is critical to real-world machine learning (ML) applications, especially for delay-sensitive tasks and resource-limited devices. A typical dilemma is: in order to provide complex intelligent services (e.g. smart city), we need inference results of multiple ML models, but the cost budget (e.g. GPU memory) is not enough to run all of them. In this work, we study underlying relationships among black-box ML models and propose a novel learning task: model linking, which aims to bridge the knowledge of different black-box models by learning mappings (dubbed model links) between their output spaces. We propose the design of model links which supports linking heterogeneous black-box ML models. Also, in order to address the distribution discrepancy challenge, we present adaptation and aggregation methods of model links. Based on our proposed model links, we developed a scheduling algorithm, named MLink. Through collaborative multi-model inference enabled by model links, MLink can improve the accuracy of obtained inference results under the cost budget. We evaluated MLink on a multi-modal dataset with seven different ML models and two real-world video analytics systems with six ML models and 3,264 hours of video. Experimental results show that our proposed model links can be effectively built among various black-box models. Under the budget of GPU memory, MLink can save 66.7% inference computations while preserving 94% inference accuracy, which outperforms multi-task learning, deep reinforcement learning-based scheduler and frame filtering baselines.
Many NLP tasks benefit from using large language models (LLMs) that often have more than 100 billion parameters. With the release of BLOOM-176B and OPT-175B, everyone can download pretrained models of this scale. Still, using these models requires high-end hardware unavailable to many researchers. In some cases, LLMs can be used more affordably via RAM offloading or hosted APIs. However, these techniques have innate limitations: offloading is too slow for interactive inference, while APIs are not flexible enough for research that requires access to weights, attention or logits. In this work, we propose Petals - a system for inference and fine-tuning of large models collaboratively by joining the resources of multiple parties. We demonstrate that this strategy outperforms offloading for very large models, running inference of BLOOM-176B on consumer GPUs with $\approx$ 1 step per second, which is enough for many interactive LLM applications. Unlike most inference APIs, Petals also natively exposes hidden states of served models, allowing to train and share custom model extensions based on efficient fine-tuning methods.
Artificial intelligence (AI) technologies, and particularly deep learning systems, are traditionally the domain of large-scale cloud servers, which have access to high computational and energy resources. Nonetheless, in Internet-of-Things (IoT) networks, the interface with the real-world is carried out using edge devices that are limited in hardware and can communicate. The conventional approach to provide AI processing to data collected by edge devices involves sending samples to the cloud, at the cost of latency, communication, connectivity, and privacy concerns. Consequently, recent years have witnessed a growing interest in enabling AI-aided inference on edge devices by leveraging their communication capabilities to establish collaborative inference. This article reviews candidate strategies for facilitating the transition of AI to IoT devices via collaboration. We identify the need to operate in different mobility and connectivity constraints as a motivating factor to consider multiple schemes, which can be roughly divided into methods where inference is done remotely, i.e., on the cloud, and those that infer on the edge. We identify the key characteristics of each strategy in terms of inference accuracy, communication latency, privacy, and connectivity requirements, providing a systematic comparison between existing approaches. We conclude by presenting future research challenges and opportunities arising from the concept of collaborative inference.
With the wide application of face recognition systems, there is rising concern that original face images could be exposed to malicious intents and consequently cause personal privacy breaches. This paper presents DuetFace, a novel privacy-preserving face recognition method that employs collaborative inference in the frequency domain. Starting from a counterintuitive discovery that face recognition can achieve surprisingly good performance with only visually indistinguishable high-frequency channels, this method designs a credible split of frequency channels by their cruciality for visualization and operates the server-side model on non-crucial channels. However, the model degrades in its attention to facial features due to the missing visual information. To compensate, the method introduces a plug-in interactive block to allow attention transfer from the client-side by producing a feature mask. The mask is further refined by deriving and overlaying a facial region of interest (ROI). Extensive experiments on multiple datasets validate the effectiveness of the proposed method in protecting face images from undesired visual inspection, reconstruction, and identification while maintaining high task availability and performance. Results show that the proposed method achieves a comparable recognition accuracy and computation cost to the unprotected ArcFace and outperforms the state-of-the-art privacy-preserving methods. The source code is available at https://github.com/Tencent/TFace/tree/master/recognition/tasks/duetface.
Radio frequency fingerprint identification (RFFI) is an emerging device authentication technique, which exploits the hardware characteristics of the RF front-end as device identifiers. RFFI is implemented in the wireless receiver and acts to extract the transmitter impairments and then perform classification. The receiver hardware impairments will actually interfere with the feature extraction process, but its effect and mitigation have not been comprehensively studied. In this paper, we propose a receiver-agnostic RFFI system that is not sensitive to the changes in receiver characteristics; it is implemented by employing adversarial training to learn the receiver-independent features. Moreover, when there are multiple receivers, this functionality can perform collaborative inference to enhance classification accuracy. Finally, we show how it is possible to leverage fine-tuning for further improvement with fewer collected signals. To validate the approach, we have conducted extensive experimental evaluation by applying the approach to a LoRaWAN case study involving ten LoRa devices and 20 software-defined radio (SDR) receivers. The results show that receiver-agnostic training enables the trained neural network to become robust to changes in receiver characteristics. The collaborative inference improves classification accuracy by up to 20% beyond a single-receiver RFFI system and fine-tuning can bring a 40% improvement for under-performing receivers.
Deep learning-based virtual staining was developed to introduce image contrast to label-free tissue sections, digitally matching the histological staining, which is time-consuming, labor-intensive, and destructive to tissue. Standard virtual staining requires high autofocusing precision during the whole slide imaging of label-free tissue, which consumes a significant portion of the total imaging time and can lead to tissue photodamage. Here, we introduce a fast virtual staining framework that can stain defocused autofluorescence images of unlabeled tissue, achieving equivalent performance to virtual staining of in-focus label-free images, also saving significant imaging time by lowering the microscope's autofocusing precision. This framework incorporates a virtual-autofocusing neural network to digitally refocus the defocused images and then transforms the refocused images into virtually stained images using a successive network. These cascaded networks form a collaborative inference scheme: the virtual staining model regularizes the virtual-autofocusing network through a style loss during the training. To demonstrate the efficacy of this framework, we trained and blindly tested these networks using human lung tissue. Using 4x fewer focus points with 2x lower focusing precision, we successfully transformed the coarsely-focused autofluorescence images into high-quality virtually stained H&E images, matching the standard virtual staining framework that used finely-focused autofluorescence input images. Without sacrificing the staining quality, this framework decreases the total image acquisition time needed for virtual staining of a label-free whole-slide image (WSI) by ~32%, together with a ~89% decrease in the autofocusing time, and has the potential to eliminate the laborious and costly histochemical staining process in pathology.
Collaborative inference has received significant research interest in machine learning as a vehicle for distributing computation load, reducing latency, as well as addressing privacy preservation in communications. Recent collaborative inference frameworks have adopted dynamic inference methodologies such as early-exit and run-time partitioning of neural networks. However, as machine learning frameworks scale in the number of inference inputs, e.g., in surveillance applications, fault tolerance related to device failure needs to be considered. This paper presents the Edge-PRUNE distributed computing framework, built on a formally defined model of computation, which provides a flexible infrastructure for fault tolerant collaborative inference. The experimental section of this work shows results on achievable inference time savings by collaborative inference, presents fault tolerant system topologies and analyzes their cost in terms of execution time overhead.
The success of deep neural networks (DNNs) is heavily dependent on computational resources. While DNNs are often employed on cloud servers, there is a growing need to operate DNNs on edge devices. Edge devices are typically limited in their computational resources, yet, often multiple edge devices are deployed in the same environment and can reliably communicate with each other. In this work we propose to facilitate the application of DNNs on the edge by allowing multiple users to collaborate during inference to improve their accuracy. Our mechanism, coined {\em edge ensembles}, is based on having diverse predictors at each device, which form an ensemble of models during inference. To mitigate the communication overhead, the users share quantized features, and we propose a method for aggregating multiple decisions into a single inference rule. We analyze the latency induced by edge ensembles, showing that its performance improvement comes at the cost of a minor additional delay under common assumptions on the communication network. Our experiments demonstrate that collaborative inference via edge ensembles equipped with compact DNNs substantially improves the accuracy over having each user infer locally, and can outperform using a single centralized DNN larger than all the networks in the ensemble together.
Recently, deploying deep neural network (DNN) models via collaborative inference, which splits a pre-trained model into two parts and executes them on user equipment (UE) and edge server respectively, becomes attractive. However, the large intermediate feature of DNN impedes flexible decoupling, and existing approaches either focus on the single UE scenario or simply define tasks considering the required CPU cycles, but ignore the indivisibility of a single DNN layer. In this paper, we study the multi-agent collaborative inference scenario, where a single edge server coordinates the inference of multiple UEs. Our goal is to achieve fast and energy-efficient inference for all UEs. To achieve this goal, we first design a lightweight autoencoder-based method to compress the large intermediate feature. Then we define tasks according to the inference overhead of DNNs and formulate the problem as a Markov decision process (MDP). Finally, we propose a multi-agent hybrid proximal policy optimization (MAHPPO) algorithm to solve the optimization problem with a hybrid action space. We conduct extensive experiments with different types of networks, and the results show that our method can reduce up to 56\% of inference latency and save up to 72\% of energy consumption.
Collaborative Inference (CI) optimizes the latency and energy consumption of deep learning inference through the inter-operation of edge and cloud devices. Albeit beneficial for other tasks, CI has never been applied to the sequence- to-sequence mapping problem at the heart of Neural Machine Translation (NMT). In this work, we address the specific issues of collaborative NMT, such as estimating the latency required to generate the (unknown) output sequence, and show how existing CI methods can be adapted to these applications. Our experiments show that CI can reduce the latency of NMT by up to 44% compared to a non-collaborative approach.
We present a chatbot implementing a novel dialogue management approach based on logical inference. Instead of framing conversation a sequence of response generation tasks, we model conversation as a collaborative inference process in which speakers share information to synthesize new knowledge in real time. Our chatbot pipeline accomplishes this modelling in three broad stages. The first stage translates user utterances into a symbolic predicate representation. The second stage then uses this structured representation in conjunction with a larger knowledge base to synthesize new predicates using efficient graph matching. In the third and final stage, our bot selects a small subset of predicates and translates them into an English response. This approach lends itself to understanding latent semantics of user inputs, flexible initiative taking, and responses that are novel and coherent with the dialogue context.
Self-supervised learning has been shown to be very effective in learning useful representations, and yet much of the success is achieved in data types such as images, audio, and text. The success is mainly enabled by taking advantage of spatial, temporal, or semantic structure in the data through augmentation. However, such structure may not exist in tabular datasets commonly used in fields such as healthcare, making it difficult to design an effective augmentation method, and hindering a similar progress in tabular data setting. In this paper, we introduce a new framework, Subsetting features of Tabular data (SubTab), that turns the task of learning from tabular data into a multi-view representation learning problem by dividing the input features to multiple subsets. We argue that reconstructing the data from the subset of its features rather than its corrupted version in an autoencoder setting can better capture its underlying latent representation. In this framework, the joint representation can be expressed as the aggregate of latent variables of the subsets at test time, which we refer to as collaborative inference. Our experiments show that the SubTab achieves the state of the art (SOTA) performance of 98.31% on MNIST in tabular setting, on par with CNN-based SOTA models, and surpasses existing baselines on three other real-world datasets by a significant margin.
The traditional convolution neural networks (CNN) have several drawbacks like the Picasso effect and the loss of information by the pooling layer. The Capsule network (CapsNet) was proposed to address these challenges because its architecture can encode and preserve the spatial orientation of input images. Similar to traditional CNNs, CapsNet is also vulnerable to several malicious attacks, as studied by several researchers in the literature. However, most of these studies focus on single-device-based inference, but horizontally collaborative inference in state-of-the-art systems, like intelligent edge services in self-driving cars, voice controllable systems, and drones, nullify most of these analyses. Horizontal collaboration implies partitioning the trained CNN models or CNN tasks to multiple end devices or edge nodes. Therefore, it is imperative to examine the robustness of the CapsNet against malicious attacks when deployed in horizontally collaborative environments. Towards this, we examine the robustness of the CapsNet when subjected to noise-based inference attacks in a horizontal collaborative environment. In this analysis, we perturbed the feature maps of the different layers of four DNN models, i.e., CapsNet, Mini-VGG, LeNet, and an in-house designed CNN (ConvNet) with the same number of parameters as CapsNet, using two types of noised-based attacks, i.e., Gaussian Noise Attack and FGSM noise attack. The experimental results show that similar to the traditional CNNs, depending upon the access of the attacker to the DNN layer, the classification accuracy of the CapsNet drops significantly. For example, when Gaussian Noise Attack classification is performed at the DigitCap layer of the CapsNet, the maximum classification accuracy drop is approximately 97%.
Collaborative inference enables resource-constrained edge devices to make inferences by uploading inputs (e.g., images) to a server (i.e., cloud) where the heavy deep learning models run. While this setup works cost-effectively for successful inferences, it severely underperforms when the model faces input samples on which the model was not trained (known as Out-of-Distribution (OOD) samples). If the edge devices could, at least, detect that an input sample is an OOD, that could potentially save communication and computation resources by not uploading those inputs to the server for inference workload. In this paper, we propose a novel lightweight OOD detection approach that mines important features from the shallow layers of a pretrained CNN model and detects an input sample as ID (In-Distribution) or OOD based on a distance function defined on the reduced feature space. Our technique (a) works on pretrained models without any retraining of those models, and (b) does not expose itself to any OOD dataset (all detection parameters are obtained from the ID training dataset). To this end, we develop EARLIN (EARLy OOD detection for Collaborative INference) that takes a pretrained model and partitions the model at the OOD detection layer and deploys the considerably small OOD part on an edge device and the rest on the cloud. By experimenting using real datasets and a prototype implementation, we show that our technique achieves better results than other approaches in terms of overall accuracy and cost when tested against popular OOD datasets on top of popular deep learning models pretrained on benchmark datasets.
Split-learning (SL) has recently gained popularity due to its inherent privacy-preserving capabilities and ability to enable collaborative inference for devices with limited computational power. Standard SL algorithms assume an ideal underlying digital communication system and ignore the problem of scarce communication bandwidth. However, for a large number of agents, limited bandwidth resources, and time-varying communication channels, the communication bandwidth can become the bottleneck. To address this challenge, in this work, we propose a novel SL framework to solve the remote inference problem that introduces an additional layer at the agent side and constrains the choices of the weights and the biases to ensure over the air aggregation. Hence, the proposed approach maintains constant communication cost with respect to the number of agents enabling remote inference under limited bandwidth. Numerical results show that our proposed algorithm significantly outperforms the digital implementation in terms of communication-efficiency, especially as the number of agents grows large.
Today's intelligent applications can achieve high performance accuracy using machine learning (ML) techniques, such as deep neural networks (DNNs). Traditionally, in a remote DNN inference problem, an edge device transmits raw data to a remote node that performs the inference task. However, this may incur high transmission energy costs and puts data privacy at risk. In this paper, we propose a technique to reduce the total energy bill at the edge device by utilizing model compression and time-varying model split between the edge and remote nodes. The time-varying representation accounts for time-varying channels and can significantly reduce the total energy at the edge device while maintaining high accuracy (low loss). We implement our approach in an image classification task using the MNIST dataset, and the system environment is simulated as a trajectory navigation scenario to emulate different channel conditions. Numerical simulations show that our proposed solution results in minimal energy consumption and $CO_2$ emission compared to the considered baselines while exhibiting robust performance across different channel conditions and bandwidth regime choices.