Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. However, existing works applying KD to QAT require tedious hyper-parameter tuning to balance the weights of different loss terms, assume the availability of labeled training data, and require complex, computationally intensive training procedures for good performance. To address these limitations, this paper proposes a novel Self-Supervised Quantization-Aware Knowledge Distillation (SQAKD) framework. SQAKD first unifies the forward and backward dynamics of various quantization functions, making it flexible for incorporating various QAT works. Then it formulates QAT as a co-optimization problem that simultaneously minimizes the KL-Loss between the full-precision and low-bit models for KD and the discretization error for quantization, without supervision from labels. A comprehensive evaluation shows that SQAKD substantially outperforms the state-of-the-art QAT and KD works for a variety of model architectures. Our code is at: https://github.com/kaiqi123/SQAKD.git.
Crowd management is crucial for a smart campus. Popular methods are camera-based. However, conventional camera-based approaches may leak users' personally identifiable features, jeopardizing user's privacy, which limits its application. In this work, we investigate using affordable light detection and ranging (LiDAR) technology to perform outdoor crowd management leveraging edge computing. Specifically, we aim to count the number of people on a walkway of a university campus. Besides privacy protection, LiDAR sensors are superior to cameras since their performance will not be compromised when the campus is not well-illuminated. We deploy LiDAR sensors on light poles to collect data from the crowd on the campus and leverage edge accelerators to process data locally. We proposed two different methodologies in this work: 1) a non-convolutional neural network (CNN)-based approach, using clustering and autoencoder, and 2) a CNN-based approach that first projects point clouds to 2D planes and then processes the projection with conventional CNNs. Our first approach relies on careful feature engineering, whereas our second approach does not require such effort. However, the CNN-based approach requires more computational power than our non-CNN-based approach. We evaluate both approaches comprehensively with our hand-labeled real-life data collected from campus. Our evaluation results show that the first method achieves an accuracy of 85.4%, whereas the second method achieves 95.8%. Our CNN-based method outperforms existing solutions significantly. We also deploy our two models on an edge accelerator, TPU, to measure the speedup, leveraging this specialized accelerator.
Digital network twin (DNT) is a promising paradigm to replicate real-world cellular networks toward continual assessment, proactive management, and what-if analysis. Existing discussions have been focusing on using only deep learning techniques to build DNTs, which raises widespread concerns regarding their generalization, explainability, and transparency. In this paper, we explore an alternative approach to augment network simulators with context-aware neural agents. The main challenge lies in the non-trivial simulation-to-reality (sim-to-real) discrepancy between offline simulators and real-world networks. To solve the challenge, we propose a new learn-to-bridge algorithm to cost-efficiently bridge the sim-to-real discrepancy in two alternative stages. In the first stage, we select states to query performances in real-world networks by using newly-designed cost-aware Bayesian optimization. In the second stage, we train the neural agent to learn the state context and bridge the probabilistic discrepancy based on Bayesian neural networks (BNN). In addition, we build a small-scale end-to-end network testbed based on OpenAirInterface RAN and Core with USRP B210 and a smartphone, and replicate the network in NS-3. The evaluation results show that, our proposed solution substantially outperforms existing methods, with more than 92\% reduction in the sim-to-real discrepancy.
Quantization-aware training (QAT) starts with a pre-trained full-precision model and performs quantization during retraining. However, existing QAT works require supervision from the labels and they suffer from accuracy loss due to reduced precision. To address these limitations, this paper proposes a novel Self-Supervised Quantization-Aware Knowledge Distillation framework (SQAKD). SQAKD first unifies the forward and backward dynamics of various quantization functions and then reframes QAT as a co-optimization problem that simultaneously minimizes the KL-Loss and the discretization error, in a self-supervised manner. The evaluation shows that SQAKD significantly improves the performance of various state-of-the-art QAT works. SQAKD establishes stronger baselines and does not require extensive labeled training data, potentially making state-of-the-art QAT research more accessible.
Large language models (LLMs) have the potential to transform our lives and work through the content they generate, known as AI-Generated Content (AIGC). To harness this transformation, we need to understand the limitations of LLMs. Here, we investigate the bias of AIGC produced by seven representative LLMs, including ChatGPT and LLaMA. We collect news articles from The New York Times and Reuters, both known for their dedication to provide unbiased news. We then apply each examined LLM to generate news content with headlines of these news articles as prompts, and evaluate the gender and racial biases of the AIGC produced by the LLM by comparing the AIGC and the original news articles. We further analyze the gender bias of each LLM under biased prompts by adding gender-biased messages to prompts constructed from these news headlines. Our study reveals that the AIGC produced by each examined LLM demonstrates substantial gender and racial biases. Moreover, the AIGC generated by each LLM exhibits notable discrimination against females and individuals of the Black race. Among the LLMs, the AIGC generated by ChatGPT demonstrates the lowest level of bias, and ChatGPT is the sole model capable of declining content generation when provided with biased prompts.
Sentiment analysis is a crucial task that aims to understand people's emotional states and predict emotional categories based on multimodal information. It consists of several subtasks, such as emotion recognition in conversation (ERC), aspect-based sentiment analysis (ABSA), and multimodal sentiment analysis (MSA). However, unifying all subtasks in sentiment analysis presents numerous challenges, including modality alignment, unified input/output forms, and dataset bias. To address these challenges, we propose a Task-Specific Prompt method to jointly model subtasks and introduce a multimodal generative framework called UniSA. Additionally, we organize the benchmark datasets of main subtasks into a new Sentiment Analysis Evaluation benchmark, SAEval. We design novel pre-training tasks and training methods to enable the model to learn generic sentiment knowledge among subtasks to improve the model's multimodal sentiment perception ability. Our experimental results show that UniSA performs comparably to the state-of-the-art on all subtasks and generalizes well to various subtasks in sentiment analysis.
A fundamental challenge of autonomous driving is maintaining the vehicle in the center of the lane by adjusting the steering angle. Recent advances leverage deep neural networks to predict steering decisions directly from images captured by the car cameras. Machine learning-based steering angle prediction needs to consider the vehicle's limitation in uploading large amounts of potentially private data for model training. Federated learning can address these constraints by enabling multiple vehicles to collaboratively train a global model without sharing their private data, but it is difficult to achieve good accuracy as the data distribution is often non-i.i.d. across the vehicles. This paper presents a new confidence-based federated distillation method to improve the performance of federated learning for steering angle prediction. Specifically, it proposes the novel use of entropy to determine the predictive confidence of each local model, and then selects the most confident local model as the teacher to guide the learning of the global model. A comprehensive evaluation of vision-based lane centering shows that the proposed approach can outperform FedAvg and FedDF by 11.3% and 9%, respectively.
Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot efficiently run on commodity hardware; and they often require users to manually explore and tune the pruning process, which is time-consuming and often leads to sub-optimal results. To address these limitations, this paper presents Automatic Attention Pruning (AAP), an adaptive, attention-based, structured pruning approach to automatically generate small, accurate, and hardware-efficient models that meet user objectives. First, it proposes iterative structured pruning using activation-based attention maps to effectively identify and prune unimportant filters. Then, it proposes adaptive pruning policies for automatically meeting the pruning objectives of accuracy-critical, memory-constrained, and latency-sensitive tasks. A comprehensive evaluation shows that AAP substantially outperforms the state-of-the-art structured pruning works for a variety of model architectures. Our code is at: https://github.com/kaiqi123/Automatic-Attention-Pruning.git.
Knowledge Transfer (KT) achieves competitive performance and is widely used for image classification tasks in model compression and transfer learning. Existing KT works transfer the information from a large model ("teacher") to train a small model ("student") by minimizing the difference of their conditionally independent output distributions. However, these works overlook the high-dimension structural knowledge from the intermediate representations of the teacher, which leads to limited effectiveness, and they are motivated by various heuristic intuitions, which makes it difficult to generalize. This paper proposes a novel Contrastive Knowledge Transfer Framework (CKTF), which enables the transfer of sufficient structural knowledge from the teacher to the student by optimizing multiple contrastive objectives across the intermediate representations between them. Also, CKTF provides a generalized agreement to existing KT techniques and increases their performance significantly by deriving them as specific cases of CKTF. The extensive evaluation shows that CKTF consistently outperforms the existing KT works by 0.04% to 11.59% in model compression and by 0.4% to 4.75% in transfer learning on various models and datasets.
The modern dynamic and heterogeneous network brings differential environments with respective state transition probability to agents, which leads to the local strategy trap problem of traditional federated reinforcement learning (FRL) based network optimization algorithm. To solve this problem, we propose a novel Differentiated Federated Reinforcement Learning (DFRL), which evolves the global policy model integration and local inference with the global policy model in traditional FRL to a collaborative learning process with parallel global trends learning and differential local policy model learning. In the DFRL, the local policy learning model is adaptively updated with the global trends model and local environment and achieves better differentiated adaptation. We evaluate the outperformance of the proposal compared with the state-of-the-art FRL in a classical CartPole game with heterogeneous environments. Furthermore, we implement the proposal in the heterogeneous Space-air-ground Integrated Network (SAGIN) for the classical traffic offloading problem in network. The simulation result shows that the proposal shows better global performance and fairness than baselines in terms of throughput, delay, and packet drop rate.