More Like this

1. Learning multi-layer latent variable model with short run MCMC inference dynamics

   Nijkamp, E.; Pang, B.; Han, T.; Zhou, L.; Zhu, S. C.; Wu, Y. N. (January 2021, European Conference on Computer Vision)

   This paper studies the fundamental problem of learning deep generative models that consist of multiple layers of latent variables organized in top-down architectures. Such models have high expressivity and allow for learning hierarchical representations. Learning such a generative model requires inferring the latent variables for each training example based on the posterior distribution of these latent variables. The inference typically requires Markov chain Monte Caro (MCMC) that can be time consuming. In this paper, we propose to use noise initialized non-persistent short run MCMC, such as nite step Langevin dynamics initialized from the prior distribution of the latent variables, as an approximate inference engine, where the step size of the Langevin dynamics is variationally optimized by minimizing the Kullback-Leibler divergence between the distribution produced by the short run MCMC and the posterior distribution. Our experiments show that the proposed method outperforms variational auto-encoder (VAE) in terms of reconstruction error and synthesis quality. The advantage of the proposed method is that it is simple and automatic without the need to design an inference model. 

   more » « less
2. Deep generative model with hierarchical latent factors for time series anomaly detection.

   Challu, C.; Jiang, P.; Wu, Y. N.; Callot, L. (January 2022, International Conference on Artificial Intelligence and Statistics (AISTAT 2022))

   Multivariate time series anomaly detection has become an active area of research in recent years, with Deep Learning models outperforming previous approaches on benchmark datasets. Among reconstruction-based models, most previous work has focused on Variational Autoencoders and Generative Adversarial Networks. This work presents DGHL, a new family of generative models for time series anomaly detection, trained by maximizing the observed likelihood by posterior sampling and alternating back-propagation. A top-down Convolution Network maps a novel hierarchical latent space to time series windows, exploiting temporal dynamics to encode information efficiently. Despite relying on posterior sampling, it is computationally more efficient than current approaches, with up to 10x shorter training times than RNN based models. Our method outperformed current state-of-the-art models on four popular benchmark datasets. Finally, DGHL is robust to variable features between entities and accurate even with large proportions of missing values, settings with increasing relevance with the advent of IoT. We demonstrate the superior robustness of DGHL with novel occlusion experiments in this literature. Our code is available at https://github. com/cchallu/dghl. 

   more » « less
3. Generative text modeling through short run inference

   Pang, B.; Nijkamp, E.; Han, T.; Wu, Y. N. (January 2021, Conference of the European Chapter of the Association for Computational Linguistics)

   Latent variable models for text, when trained successfully, accurately model the data distribution and capture global semantic and syntactic features of sentences. The prominent approach to train such models is variational autoencoders (VAE). It is nevertheless challenging to train and often results in a trivial local optimum where the latent variable is ignored and its posterior collapses into the prior, an issue known as posterior collapse. Various techniques have been proposed to mitigate this issue. Most of them focus on improving the inference model to yield latent codes of higher quality. The present work proposes a short run dynamics for inference. It is initialized from the prior distribution of the latent variable and then runs a small number (e.g., 20) of Langevin dynamics steps guided by its posterior distribution. The major advantage of our method is that it does not require a separate inference model or assume simple geometry of the posterior distribution, thus rendering an automatic, natural and flexible inference engine. We show that the models trained with short run dynamics more accurately model the data, compared to strong language model and VAE baselines, and exhibit no sign of posterior collapse. Analyses of the latent space show that interpolation in the latent space is able to generate coherent sentences with smooth transition and demonstrate improved classification over strong baselines with latent features from unsupervised pretraining. These results together expose a well-structured latent space of our generative model. 

   more » « less
4. Normalizing Flows for Intelligent Manufacturing

   https://doi.org/10.1115/MSEC2023-101281  

   Russell, Matthew; Wang, Peng (June 2023, American Society of Mechanical Engineers)

   Abstract Monitoring machine health and product quality enables predictive maintenance that optimizes repairs to minimize factory downtime. Data-driven intelligent manufacturing often relies on probabilistic techniques with intractable distributions. For example, generative models of data distributions can balance fault classes with synthetic data, and sampling the posterior distribution of hidden model parameters enables prognosis of degradation trends. Normalizing flows can address these problems while avoiding the training instability or long inference times of other generative Deep Learning (DL) models like Generative Adversarial Networks (GAN), Variational Autoencoders (VAE), and diffusion networks. To evaluate normalizing flows for manufacturing, experiments are conducted to synthesize surface defect images from an imbalanced data set and estimate parameters of a tool wear degradation model from limited observations. Results show that normalizing flows are an effective, multi-purpose DL architecture for solving these problems in manufacturing. Future work should explore normalizing flows for more complex degradation models and develop a framework for likelihood-based anomaly detection. Code is available at https://github.com/uky-aism/flows-for-manufacturing. 

   more » « less
5. Influence-aware attention for multivariate temporal point processes

   Shou, Xiao; Gao, Tian; Subramanian, Dharmashankar; Bhattacharjya, Debarun; Bennett, Kristin (April 2024, Conference on Causal Learning and Reasoning)

   Identifying the subset of events that influence events of interest from continuous time datasets is of great interest in various applications. Existing methods however often fail to produce accurate and interpretable results in a time-efficient manner. In this paper, we propose a neural model – Influence-Aware Attention for Multivariate Temporal Point Processes (IAA-MTPPs) – which leverages the powerful attention mechanism in transformers to capture temporal dynamics between event types, which is different from existing instance-to-instance attentions, using variational inference while maintaining interpretability. Given event sequences and a prior influence matrix, IAA-MTPP efficiently learns an approximate posterior by an Attention-to-Influence mechanism, and subsequently models the conditional likelihood of the sequences given a sampled influence through an Influence-to-Attention formulation. Both steps are completed efficiently inside a B-block multi-head self-attention layer, thus our end-to-end training with parallelizable transformer architecture enables faster training compared to sequential models such as RNNs. We demonstrate strong empirical performance compared to existing baselines on multiple synthetic and real benchmarks, including qualitative analysis for an application in decentralized finance. 

   more » « less