Quanquan Gu works at University of California, Los Angeles.

Posts

State-Aware Anomaly Detection for Massive Sensor Data in Internet of Things

/in /by

With the escalating prevalence of Internet of Things (IoTs) in critical infrastructure, the requirement for efficient and effective anomaly detection solution becomes increasingly important. Unfortunately, most prior research works have largely overlooked to adapt detection criteria for different operational states, thereby rendering them inadequate when confronted with diverse and complex work states of IoTs. In this study, we address the challenges of IoT anomaly detection across various work states by introducing a novel model called Hybrid State Encoder-Decoder (HSED). HSED employs a two-step approach, beginning with identification and construction of a hybrid state for Key Performance Indicator (KPI) sensors based on their state attributes, followed by the detection of abnormal or failure events utilizing high-dimensional sensor data. Through the evaluation on real-world datasets, we demonstrate the superiority of HSED over state-of-the-art anomaly detection models. HSED can significantly enhance the efficiency, adaptability and reliability of IoTs and avoid potential risks of economic losses by IoT failures.

Read more

Personalized Federated Learning under Mixture Distributions

/in /by

The recent trend towards Personalized Federated Learning (PFL) has garnered significant attention as it allows for the training of models that are tailored to each client while maintaining data privacy. However, current PFL techniques primarily focus on modeling the conditional distribution heterogeneity (i.e. concept shift), which can result in suboptimal performance when the distribution of input data across clients diverges (i.e. covariate shift). Additionally, these techniques often lack the ability to adapt to unseen data, further limiting their effectiveness in real-world scenarios. To address these limitations, we propose a novel approach, FedGMM, which utilizes Gaussian mixture models (GMM) to effectively fit the input data distributions across diverse clients. The model parameters are estimated by maximum likelihood estimation utilizing a federated Expectation-Maximization algorithm, which is solved in closed form and does not assume gradient similarity. Furthermore, FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.

Read more

Beyond One Model Fits All: A Survey of Domain Specialization for Large Language Models

/in /by

Large language models (LLMs) have significantly advanced the field of natural language processing (NLP), providing a highly useful, task agnostic foundation for a wide range of applications. The great promise of LLMs as general task solvers motivated people to extend their functionality largely beyond just a “chatbot”, and use it as an assistant or even replacement for domain experts and tools in specific domains such as healthcare, finance, and education. However, directly applying LLMs to solve sophisticated problems in specific domains meets many hurdles, caused by the heterogeneity of domain data, the sophistication of domain knowledge, the uniqueness of domain objectives, and the diversity of the constraints (e.g., various social norms, cultural conformity, religious beliefs, and ethical standards in the domain applications). To fill such a gap, explosively increase research, and practices have been conducted in very recent years on the domain specialization of LLMs, which, however, calls for a comprehensive and systematic review to better summarizes and guide this promising domain. In this survey paper, first, we propose a systematic taxonomy that categorizes the LLM domain specialization techniques based on the accessibility to LLMs and summarizes the framework for all the subcategories as well as their relations and differences to each other. We also present a comprehensive taxonomy of critical application domains that can benefit from specialized LLMs, discussing their practical significance and open challenges. Furthermore, we offer insights into the current research status and future trends in this area.

Read more