Chaoran Huang

Tengji Xu, Zeyu Luo, Shaojie Liu et al.

AI models are essential in science and engineering, but recent advances are pushing the limits of traditional digital hardware. To address these limitations, physical neural networks (PNNs), which use physical substrates for computation, have gained increasing attention. However, developing effective training methods for PNNs remains a significant challenge. Current approaches, regardless of offline and online training, suffer from significant accuracy loss. Offline training is hindered by imprecise modeling, while online training yields device-specific models that can't be transferred to other devices due to manufacturing variances. Both methods face challenges from perturbations after deployment, such as thermal drift or alignment errors, which make trained models invalid and require retraining. Here, we address the challenges with both offline and online training through a novel technique called Sharpness-Aware Training (SAT), where we innovatively leverage the geometry of the loss landscape to tackle the problems in training physical systems. SAT enables accurate training using efficient backpropagation algorithms, even with imprecise models. PNNs trained by SAT offline even outperform those trained online, despite modeling and fabrication errors. SAT also overcomes online training limitations by enabling reliable transfer of models between devices. Finally, SAT is highly resilient to perturbations after deployment, allowing PNNs to continuously operate accurately under perturbations without retraining. We demonstrate SAT across three types of PNNs, showing it is universally applicable, regardless of whether the models are explicitly known. This work offers a transformative, efficient approach to training PNNs, addressing critical challenges in analog computing and enabling real-world deployment.

Benshan Wang, Qiarong Xiao, Tengji Xu et al.

The rapid expansion of generative AI drives unprecedented demands for high-performance computing. Training large-scale AI models now requires vast interconnected GPU clusters across multiple data centers. Multi-scale AI training and inference demand uniform, ultra-low latency, and energy-efficient links to enable massive GPUs to function as a single cohesive unit. However, traditional electrical and optical interconnects, relying on conventional digital signal processors (DSPs) for signal distortion compensation, increasingly fail to meet these stringent requirements. To overcome these limitations, we present an integrated neuromorphic optical signal processor (OSP) that leverages deep reservoir computing and achieves DSP-free, all-optical, real-time processing. Experimentally, our OSP achieves a 100 Gbaud PAM4 per lane, 1.6 Tbit/s data center interconnect over a 5 km optical fiber in the C-band (equivalent to over 80 km in the O-band), far exceeding the reach of state-of-the-art DSP solutions, which are fundamentally constrained by chromatic dispersion in IMDD systems. Simultaneously, it reduces processing latency by four orders of magnitude and energy consumption by three orders of magnitude. Unlike DSPs, which introduce increased latency at high data rates, our OSP maintains consistent, ultra-low latency regardless of data rate scaling, making it ideal for future optical interconnects. Moreover, the OSP retains full optical field information for better impairment compensation and adapts to various modulation formats, data rates, and wavelengths. Fabricated using a mature silicon photonic process, the OSP can be monolithically integrated with silicon photonic transceivers, enhancing the compactness and reliability of all-optical interconnects. This research provides a highly scalable, energy-efficient, and high-speed solution, paving the way for next-generation AI infrastructure.

Hsuan-Tung Peng, Joshua Lederman, Lei Xu et al.

Machine learning (ML) methods are ubiquitous in wireless communication systems and have proven powerful for applications including radio-frequency (RF) fingerprinting, automatic modulation classification, and cognitive radio. However, the large size of ML models can make them difficult to implement on edge devices for latency-sensitive downstream tasks. In wireless communication systems, ML data processing at a sub-millisecond scale will enable real-time network monitoring to improve security and prevent infiltration. In addition, compact and integratable hardware platforms which can implement ML models at the chip scale will find much broader application to wireless communication networks. Toward real-time wireless signal classification at the edge, we propose a novel compact deep network that consists of a photonic-hardware-inspired recurrent neural network model in combination with a simplified convolutional classifier, and we demonstrate its application to the identification of RF emitters by their random transmissions. With the proposed model, we achieve 96.32% classification accuracy over a set of 30 identical ZigBee devices when using 50 times fewer training parameters than an existing state-of-the-art CNN classifier. Thanks to the large reduction in network size, we demonstrate real-time RF fingerprinting with 0.219 ms latency using a small-scale FPGA board, the PYNQ-Z1.

May Altulyan, Lina Yao, Xianzhi Wang et al.

Recommendation represents a vital stage in developing and promoting the benefits of the Internet of Things (IoT). Traditional recommender systems fail to exploit ever-growing, dynamic, and heterogeneous IoT data. This paper presents a comprehensive review of the state-of-the-art recommender systems, as well as related techniques and application in the vibrant field of IoT. We discuss several limitations of applying recommendation systems to IoT and propose a reference framework for comparing existing studies to guide future research and practices.

Xiaocong Chen, Chaoran Huang, Lina Yao et al.

Interactive recommendation aims to learn from dynamic interactions between items and users to achieve responsiveness and accuracy. Reinforcement learning is inherently advantageous for coping with dynamic environments and thus has attracted increasing attention in interactive recommendation research. Inspired by knowledge-aware recommendation, we proposed Knowledge-Guided deep Reinforcement learning (KGRL) to harness the advantages of both reinforcement learning and knowledge graphs for interactive recommendation. This model is implemented upon the actor-critic network framework. It maintains a local knowledge network to guide decision-making and employs the attention mechanism to capture long-term semantics between items. We have conducted comprehensive experiments in a simulated online environment with six public real-world datasets and demonstrated the superiority of our model over several state-of-the-art methods.

Chaoran Huang, Lina Yao, Xianzhi Wang et al.

Community Question Answering (CQA) websites can be claimed as the most major venues for knowledge sharing, and the most effective way of exchanging knowledge at present. Considering that massive amount of users are participating online and generating huge amount data, management of knowledge here systematically can be challenging. Expert recommendation is one of the major challenges, as it highlights users in CQA with potential expertise, which may help match unresolved questions with existing high quality answers while at the same time may help external services like human resource systems as another reference to evaluate their candidates. In this paper, we in this work we propose to exploring experts in CQA websites. We take advantage of recent distributed word representation technology to help summarize text chunks, and in a semantic view exploiting the relationships between natural language phrases to extract latent knowledge domains. By domains, the users' expertise is determined on their historical performance, and a rank can be compute to given recommendation accordingly. In particular, Stack Overflow is chosen as our dataset to test and evaluate our work, where inclusive experiment shows our competence.

Xiang Zhang, Lina Yao, Chaoran Huang et al.

Electroencephalography (EEG) signals are known to manifest differential patterns when individuals visually concentrate on different objects. In this work, we present an end-to-end digital fabrication system, Brain2Object, to print the 3D object that an individual is observing by decoding visually-evoked brain signals. We propose a unified training framework that combines multi-class Common Spatial Pattern and Convolutional Neural Networks to support the backend computation. We learn the dynamical graph representations of brain signals to accurately capture the structural information among EEG channels. A user-friendly interface is developed as the system front end. Brain2Object presents a streamlined end-to-end workflow that can serve as a template for deeper integration of BCI technologies to assist with our routine activities. The proposed system is evaluated extensively using offline experiments and through an online demonstrator. The experimental results show that our approach can achieve the recognition accuracy of 92.58% on a benchmark dataset and 75.23% on a locally collected dataset. Moreover, our method consistently outperforms a wide range of baseline and state-of-the-art approaches. The proof-of-concept corroborates the practicality of our approach and illustrates the ease with which such a system could be deployed.

Chaoran Huang, Lina Yao, Xianzhi Wang et al.

Knowledge acquisition and exchange are generally crucial yet costly for both businesses and individuals, especially when the knowledge concerns various areas. Question Answering Communities offer an opportunity for sharing knowledge at a low cost, where communities users, many of whom are domain experts, can potentially provide high-quality solutions to a given problem. In this paper, we propose a framework for finding experts across multiple collaborative networks. We employ the recent techniques of tree-guided learning (via tensor decomposition), and matrix factorization to explore user expertise from past voted posts. Tensor decomposition enables to leverage the latent expertise of users, and the posts and related tags help identify the related areas. The final result is an expertise score for every user on every knowledge area. We experiment on Stack Exchange Networks, a set of question answering websites on different topics with a huge group of users and posts. Experiments show our proposed approach produces steady and premium outputs.

Xianzhi Wang, Chaoran Huang, Lina Yao et al.

Community question answering (CQA) represents the type of Web applications where people can exchange knowledge via asking and answering questions. One significant challenge of most real-world CQA systems is the lack of effective matching between questions and the potential good answerers, which adversely affects the efficient knowledge acquisition and circulation. On the one hand, a requester might experience many low-quality answers without receiving a quality response in a brief time, on the other hand, an answerer might face numerous new questions without being able to identify their questions of interest quickly. Under this situation, expert recommendation emerges as a promising technique to address the above issues. Instead of passively waiting for users to browse and find their questions of interest, an expert recommendation method raises the attention of users to the appropriate questions actively and promptly. The past few years have witnessed considerable efforts that address the expert recommendation problem from different perspectives. These methods all have their issues that need to be resolved before the advantages of expert recommendation can be fully embraced. In this survey, we first present an overview of the research efforts and state-of-the-art techniques for the expert recommendation in CQA. We next summarize and compare the existing methods concerning their advantages and shortcomings, followed by discussing the open issues and future research directions.

Manqing Dong, Lina Yao, Xianzhi Wang et al.

Online reviews play an important role in influencing buyers' daily purchase decisions. However, fake and meaningless reviews, which cannot reflect users' genuine purchase experience and opinions, widely exist on the Web and pose great challenges for users to make right choices. Therefore,it is desirable to build a fair model that evaluates the quality of products by distinguishing spamming reviews. We present an end-to-end trainable unified model to leverage the appealing properties from Autoencoder and random forest. A stochastic decision tree model is implemented to guide the global parameter learning process. Extensive experiments were conducted on a large Amazon review dataset. The proposed model consistently outperforms a series of compared methods.

Xiang Zhang, Lina Yao, Chaoran Huang et al.

Multimodal wearable sensor data classification plays an important role in ubiquitous computing and has a wide range of applications in scenarios from healthcare to entertainment. However, most existing work in this field employs domain-specific approaches and is thus ineffective in complex sit- uations where multi-modality sensor data are col- lected. Moreover, the wearable sensor data are less informative than the conventional data such as texts or images. In this paper, to improve the adapt- ability of such classification methods across differ- ent application domains, we turn this classification task into a game and apply a deep reinforcement learning scheme to deal with complex situations dynamically. Additionally, we introduce a selective attention mechanism into the reinforcement learn- ing scheme to focus on the crucial dimensions of the data. This mechanism helps to capture extra information from the signal and thus it is able to significantly improve the discriminative power of the classifier. We carry out several experiments on three wearable sensor datasets and demonstrate the competitive performance of the proposed approach compared to several state-of-the-art baselines.

Xiang Zhang, Lina Yao, Chaoran Huang et al.

Biometric authentication involves various technologies to identify individuals by exploiting their unique, measurable physiological and behavioral characteristics. However, traditional biometric authentication systems (e.g., face recognition, iris, retina, voice, and fingerprint) are facing an increasing risk of being tricked by biometric tools such as anti-surveillance masks, contact lenses, vocoder, or fingerprint films. In this paper, we design a multimodal biometric authentication system named Deepkey, which uses both Electroencephalography (EEG) and gait signals to better protect against such risk. Deepkey consists of two key components: an Invalid ID Filter Model to block unauthorized subjects and an identification model based on attention-based Recurrent Neural Network (RNN) to identify a subject`s EEG IDs and gait IDs in parallel. The subject can only be granted access while all the components produce consistent evidence to match the user`s proclaimed identity. We implement Deepkey with a live deployment in our university and conduct extensive empirical experiments to study its technical feasibility in practice. DeepKey achieves the False Acceptance Rate (FAR) and the False Rejection Rate (FRR) of 0 and 1.0%, respectively. The preliminary results demonstrate that Deepkey is feasible, show consistent superior performance compared to a set of methods, and has the potential to be applied to the authentication deployment in real world settings.