Jaehee Jang

Jaehee Jang, Heonseok Ha, Dahuin Jung et al.

Personalized federated learning is aimed at allowing numerous clients to train personalized models while participating in collaborative training in a communication-efficient manner without exchanging private data. However, many personalized federated learning algorithms assume that clients have the same neural network architecture, and those for heterogeneous models remain understudied. In this study, we propose a novel personalized federated learning method called federated classifier averaging (FedClassAvg). Deep neural networks for supervised learning tasks consist of feature extractor and classifier layers. FedClassAvg aggregates classifier weights as an agreement on decision boundaries on feature spaces so that clients with not independently and identically distributed (non-iid) data can learn about scarce labels. In addition, local feature representation learning is applied to stabilize the decision boundaries and improve the local feature extraction capabilities for clients. While the existing methods require the collection of auxiliary data or model weights to generate a counterpart, FedClassAvg only requires clients to communicate with a couple of fully connected layers, which is highly communication-efficient. Moreover, FedClassAvg does not require extra optimization problems such as knowledge transfer, which requires intensive computation overhead. We evaluated FedClassAvg through extensive experiments and demonstrated it outperforms the current state-of-the-art algorithms on heterogeneous personalized federated learning tasks.

Byunggook Na, Jaehee Jang, Seongsik Park et al.

Various deep learning applications on smartphones have been rapidly rising, but training deep neural networks (DNNs) has too large computational burden to be executed on a single smartphone. A portable cluster, which connects smartphones with a wireless network and supports parallel computation using them, can be a potential approach to resolve the issue. However, by our findings, the limitations of wireless communication restrict the cluster size to up to 30 smartphones. Such small-scale clusters have insufficient computational power to train DNNs from scratch. In this paper, we propose a scalable smartphone cluster enabling deep learning training by removing the portability to increase its computational efficiency. The cluster connects 138 Galaxy S10+ devices with a wired network using Ethernet. We implemented large-batch synchronous training of DNNs based on Caffe, a deep learning library. The smartphone cluster yielded 90% of the speed of a P100 when training ResNet-50, and approximately 43x speed-up of a V100 when training MobileNet-v1.

Ho Bae, Jaehee Jang, Dahuin Jung et al.

To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that can compromise its integrity and efficiency. Security attacks can be divided based on when they occur: if an attack occurs during training, it is known as a poisoning attack, and if it occurs during inference (after training) it is termed an evasion attack. Poisoning attacks compromise the training process by corrupting the data with malicious examples, while evasion attacks use adversarial examples to disrupt entire classification process. Defenses proposed against such attacks include techniques to recognize and remove malicious data, train a model to be insensitive to such data, and mask the model's structure and parameters to render attacks more challenging to implement. Furthermore, the privacy of the data involved in model training is also threatened by attacks such as the model-inversion attack, or by dishonest service providers of AI applications. To maintain data privacy, several solutions that combine existing data-privacy techniques have been proposed, including differential privacy and modern cryptography techniques. In this paper, we describe the notions of some of methods, e.g., homomorphic encryption, and review their advantages and challenges when implemented in deep-learning models.

Seongsik Park, Jaehee Jang, Seijoon Kim et al.

Memory-augmented neural networks (MANNs) are designed for question-answering tasks. It is difficult to run a MANN effectively on accelerators designed for other neural networks (NNs), in particular on mobile devices, because MANNs require recurrent data paths and various types of operations related to external memory access. We implement an accelerator for MANNs on a field-programmable gate array (FPGA) based on a data flow architecture. Inference times are also reduced by inference thresholding, which is a data-based maximum inner-product search specialized for natural language tasks. Measurements on the bAbI data show that the energy efficiency of the accelerator (FLOPS/kJ) was higher than that of an NVIDIA TITAN V GPU by a factor of about 125, increasing to 140 with inference thresholding

Jaehee Jang, Byungook Na, Sungroh Yoon

Distributed training of deep neural networks has received significant research interest, and its major approaches include implementations on multiple GPUs and clusters. Parallelization can dramatically improve the efficiency of training deep and complicated models with large-scale data. A fundamental barrier against the speedup of DNN training, however, is the trade-off between computation and communication time. In other words, increasing the number of worker nodes decreases the time consumed in computation while simultaneously increasing communication overhead under constrained network bandwidth, especially in commodity hardware environments. To alleviate this trade-off, we suggest the idea of homomorphic parameter compression, which compresses parameters with the least expense and trains the DNN with the compressed representation. Although the specific method is yet to be discovered, we demonstrate that there is a high probability that the homomorphism can reduce the communication overhead, thanks to little compression and decompression times. We also provide theoretical speedup of homomorphic compression.

Hanjoo Kim, Jaehong Park, Jaehee Jang et al.

The increasing complexity of deep neural networks (DNNs) has made it challenging to exploit existing large-scale data processing pipelines for handling massive data and parameters involved in DNN training. Distributed computing platforms and GPGPU-based acceleration provide a mainstream solution to this computational challenge. In this paper, we propose DeepSpark, a distributed and parallel deep learning framework that exploits Apache Spark on commodity clusters. To support parallel operations, DeepSpark automatically distributes workloads and parameters to Caffe/Tensorflow-running nodes using Spark, and iteratively aggregates training results by a novel lock-free asynchronous variant of the popular elastic averaging stochastic gradient descent based update scheme, effectively complementing the synchronized processing capabilities of Spark. DeepSpark is an on-going project, and the current release is available at http://deepspark.snu.ac.kr.