Diffusion generative models unlock new possibilities for inverse problems as they allow for the incorporation of strong empirical priors into the process of scientific inference. Recently, diffusion models received significant attention for solving inverse problems by posterior sampling, but many challenges remain open due to the intractability of this sampling process. Prior work resorted to Gaussian approximations to conditional densities of the reverse process, leveraging Tweedie's formula to parameterise its mean, complemented with various heuristics. In this work, we leverage higher order information using Tweedie's formula and obtain a finer approximation with a principled covariance estimate. This novel approximation removes any time-dependent step-size hyperparameters required by earlier methods, and enables higher quality approximations of the posterior density which results in better samples. Specifically, we tackle noisy linear inverse problems and obtain a novel approximation to the gradient of the likelihood. We then plug this gradient estimate into various diffusion models and show that this method is optimal for a Gaussian data distribution. We illustrate the empirical effectiveness of our approach for general linear inverse problems on toy synthetic examples as well as image restoration using pretrained diffusion models as the prior. We show that our method improves the sample quality by providing statistically principled approximations to diffusion posterior sampling problem.
相關內容
Diffusion Language models (DLMs) are a promising avenue for text generation due to their practical properties on tractable controllable generation. They also have the advantage of not having to predict text autoregressively. However, despite these notable features, DLMs have not yet reached the performance levels of their Autoregressive counterparts. One of the ways to reduce the performance gap between these two types of language models is to speed up the generation of DLMs. Therefore, we propose a pioneering methodology to address this issue in this work. It enables the execution of more generation steps within a given time frame, potentially leading to higher-quality outputs. Specifically, our methods estimate DLMs completeness of text generation and allow adaptive halting of the generation process. We test and refine our methods on Plaid, SSD, and CDCD DLMs and create a cohesive perspective on their generation workflows. Finally, we confirm that our methods allow halting Plaid, SSD, and CDCD models and decrease the generation time by $10$-$40$% without a drop in the quality of model samples.
The retail sector presents several open and challenging problems that could benefit from advanced pattern recognition and computer vision techniques. One such critical challenge is planogram compliance control. In this study, we propose a complete embedded system to tackle this issue. Our system consists of four key components as image acquisition and transfer via stand-alone embedded camera module, object detection via computer vision and deep learning methods working on single board computers, planogram compliance control method again working on single board computers, and energy harvesting and power management block to accompany the embedded camera modules. The image acquisition and transfer block is implemented on the ESP-EYE camera module. The object detection block is based on YOLOv5 as the deep learning method and local feature extraction. We implement these methods on Raspberry Pi 4, NVIDIA Jetson Orin Nano, and NVIDIA Jetson AGX Orin as single board computers. The planogram compliance control block utilizes sequence alignment through a modified Needleman-Wunsch algorithm. This block is also working along with the object detection block on the same single board computers. The energy harvesting and power management block consists of solar and RF energy harvesting modules with suitable battery pack for operation. We tested the proposed embedded planogram compliance control system on two different datasets to provide valuable insights on its strengths and weaknesses. The results show that our method achieves F1 scores of 0.997 and 1.0 in object detection and planogram compliance control blocks, respectively. Furthermore, we calculated that the complete embedded system can work in stand-alone form up to two years based on battery. This duration can be further extended with the integration of the proposed solar and RF energy harvesting options.
Social media data is plagued by the redundancy problem caused by its noisy nature, leading to increased training time and model bias. To address this issue, we propose a novel approach called generative deduplication. It aims to remove duplicate text from noisy social media data and mitigate model bias. By doing so, it can improve social media language understanding performance and save training time. Extensive experiments demonstrate that the proposed generative deduplication can effectively reduce training samples while improving performance. This evidence suggests the effectiveness of generative deduplication and its importance in social media language understanding.
Despite the growing popularity of diffusion models, gaining a deep understanding of the model class remains somewhat elusive for the uninitiated in non-equilibrium statistical physics. With that in mind, we present what we believe is a more straightforward introduction to diffusion models using directed graphical modelling and variational Bayesian principles, which imposes relatively fewer prerequisites on the average reader. Our exposition constitutes a comprehensive technical review spanning from foundational concepts like deep latent variable models to recent advances in continuous-time diffusion-based modelling, highlighting theoretical connections between model classes along the way. We provide additional mathematical insights that were omitted in the seminal works whenever possible to aid in understanding, while avoiding the introduction of new notation. We envision this article serving as a useful educational supplement for both researchers and practitioners in the area, and we welcome feedback and contributions from the community at //github.com/biomedia-mira/demystifying-diffusion.
This paper presents a new approach for assembling graph neural networks based on framelet transforms. The latter provides a multi-scale representation for graph-structured data. With the framelet system, we can decompose the graph feature into low-pass and high-pass frequencies as extracted features for network training, which then defines a framelet-based graph convolution. The framelet decomposition naturally induces a graph pooling strategy by aggregating the graph feature into low-pass and high-pass spectra, which considers both the feature values and geometry of the graph data and conserves the total information. The graph neural networks with the proposed framelet convolution and pooling achieve state-of-the-art performance in many types of node and graph prediction tasks. Moreover, we propose shrinkage as a new activation for the framelet convolution, which thresholds the high-frequency information at different scales. Compared to ReLU, shrinkage in framelet convolution improves the graph neural network model in terms of denoising and signal compression: noises in both node and structure can be significantly reduced by accurately cutting off the high-pass coefficients from framelet decomposition, and the signal can be compressed to less than half its original size with the prediction performance well preserved.
Adversarial attack is a technique for deceiving Machine Learning (ML) models, which provides a way to evaluate the adversarial robustness. In practice, attack algorithms are artificially selected and tuned by human experts to break a ML system. However, manual selection of attackers tends to be sub-optimal, leading to a mistakenly assessment of model security. In this paper, a new procedure called Composite Adversarial Attack (CAA) is proposed for automatically searching the best combination of attack algorithms and their hyper-parameters from a candidate pool of \textbf{32 base attackers}. We design a search space where attack policy is represented as an attacking sequence, i.e., the output of the previous attacker is used as the initialization input for successors. Multi-objective NSGA-II genetic algorithm is adopted for finding the strongest attack policy with minimum complexity. The experimental result shows CAA beats 10 top attackers on 11 diverse defenses with less elapsed time (\textbf{6 $\times$ faster than AutoAttack}), and achieves the new state-of-the-art on $l_{\infty}$, $l_{2}$ and unrestricted adversarial attacks.
Knowledge graph (KG) embedding encodes the entities and relations from a KG into low-dimensional vector spaces to support various applications such as KG completion, question answering, and recommender systems. In real world, knowledge graphs (KGs) are dynamic and evolve over time with addition or deletion of triples. However, most existing models focus on embedding static KGs while neglecting dynamics. To adapt to the changes in a KG, these models need to be re-trained on the whole KG with a high time cost. In this paper, to tackle the aforementioned problem, we propose a new context-aware Dynamic Knowledge Graph Embedding (DKGE) method which supports the embedding learning in an online fashion. DKGE introduces two different representations (i.e., knowledge embedding and contextual element embedding) for each entity and each relation, in the joint modeling of entities and relations as well as their contexts, by employing two attentive graph convolutional networks, a gate strategy, and translation operations. This effectively helps limit the impacts of a KG update in certain regions, not in the entire graph, so that DKGE can rapidly acquire the updated KG embedding by a proposed online learning algorithm. Furthermore, DKGE can also learn KG embedding from scratch. Experiments on the tasks of link prediction and question answering in a dynamic environment demonstrate the effectiveness and efficiency of DKGE.
This paper is an attempt to explain all the matrix calculus you need in order to understand the training of deep neural networks. We assume no math knowledge beyond what you learned in calculus 1, and provide links to help you refresh the necessary math where needed. Note that you do not need to understand this material before you start learning to train and use deep learning in practice; rather, this material is for those who are already familiar with the basics of neural networks, and wish to deepen their understanding of the underlying math. Don't worry if you get stuck at some point along the way---just go back and reread the previous section, and try writing down and working through some examples. And if you're still stuck, we're happy to answer your questions in the Theory category at forums.fast.ai. Note: There is a reference section at the end of the paper summarizing all the key matrix calculus rules and terminology discussed here. See related articles at //explained.ai
We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon. Compared with character-based methods, our model explicitly leverages word and word sequence information. Compared with word-based methods, lattice LSTM does not suffer from segmentation errors. Gated recurrent cells allow our model to choose the most relevant characters and words from a sentence for better NER results. Experiments on various datasets show that lattice LSTM outperforms both word-based and character-based LSTM baselines, achieving the best results.
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191