Specialized compute blocks have been developed for efficient DNN execution. However, due to the vast amount of data and parameter movements, the interconnects and on-chip memories form another bottleneck, impairing power and performance. This work addresses this bottleneck by contributing a low-power technique for edge-AI inference engines that combines overhead-free coding with a statistical analysis of the data and parameters of neural networks. Our approach reduces the interconnect and memory power consumption by up to 80% for state-of-the-art benchmarks while providing additional power savings for the compute blocks by up to 39%. These power improvements are achieved with no loss of accuracy and negligible hardware cost.
相關內容
Neural Radiance Fields (NeRF) have recently emerged as a powerful method for image-based 3D reconstruction, but the lengthy per-scene optimization limits their practical usage, especially in resource-constrained settings. Existing approaches solve this issue by reducing the number of input views and regularizing the learned volumetric representation with either complex losses or additional inputs from other modalities. In this paper, we present KeyNeRF, a simple yet effective method for training NeRF in few-shot scenarios by focusing on key informative rays. Such rays are first selected at camera level by a view selection algorithm that promotes baseline diversity while guaranteeing scene coverage, then at pixel level by sampling from a probability distribution based on local image entropy. Our approach performs favorably against state-of-the-art methods, while requiring minimal changes to existing NeRF codebases.
We consider estimation of a functional parameter of a realistically modeled data distribution based on independent and identically distributed observations. Suppose that the true function is defined as the minimizer of the expectation of a specified loss function over its parameter space. Estimators of the true function are provided, viewed as a data-adaptive coordinate transformation for the true function. For any $J$-dimensional real valued cadlag function with finite sectional variation norm, we define a candidate ensemble estimator as the mapping from the data into the composition of the cadlag function and the $J$ estimated functions. Using $V$-fold cross-validation, we define the cross-validated empirical risk of each cadlag function specific ensemble estimator. We then define the Meta Highly Adaptive Lasso Minimum Loss Estimator (M-HAL-MLE) as the cadlag function that minimizes this cross-validated empirical risk over all cadlag functions with a uniform bound on the sectional variation norm. For each of the $V$ training samples, this yields a composition of the M-HAL-MLE ensemble and the $J$ estimated functions trained on the training sample. We can estimate the true function with the average of these $V$ estimated functions, which we call the M-HAL super-learner. The M-HAL super-learner converges to the oracle estimator at a rate $n^{-2/3}$ (up till $\log n$-factor) w.r.t. excess risk, where the oracle estimator minimizes the excess risk among all considered ensembles. The excess risk of the oracle estimator and true function is generally second order. Under weak conditions on the $J$ candidate estimators, target features of the undersmoothed M-HAL super-learner are asymptotically linear estimators of the corresponding target features of true function, with influence curve either the efficient influence curve, or potentially, a super-efficient influence curve.
The pests captured with imaging devices may be relatively small in size compared to the entire images, and complex backgrounds have colors and textures similar to those of the pests, which hinders accurate feature extraction and makes pest identification challenging. The key to pest identification is to create a model capable of detecting regions of interest (ROIs) and transforming them into better ones for attention and discriminative learning. To address these problems, we will study how to generate and update the ROIs via multiscale cross-attention fusion as well as how to be highly robust to complex backgrounds and scale problems. Therefore, we propose a novel ROI-aware multiscale cross-attention vision transformer (ROI-ViT). The proposed ROI-ViT is designed using dual branches, called Pest and ROI branches, which take different types of maps as input: Pest images and ROI maps. To render such ROI maps, ROI generators are built using soft segmentation and a class activation map and then integrated into the ROI-ViT backbone. Additionally, in the dual branch, complementary feature fusion and multiscale hierarchies are implemented via a novel multiscale cross-attention fusion. The class token from the Pest branch is exchanged with the patch tokens from the ROI branch, and vice versa. The experimental results show that the proposed ROI-ViT achieves 81.81%, 99.64%, and 84.66% for IP102, D0, and SauTeg pest datasets, respectively, outperforming state-of-the-art (SOTA) models, such as MViT, PVT, DeiT, Swin-ViT, and EfficientNet. More importantly, for the new challenging dataset IP102(CBSS) that contains only pest images with complex backgrounds and small sizes, the proposed model can maintain high recognition accuracy, whereas that of other SOTA models decrease sharply, demonstrating that our model is more robust to complex background and scale problems.
Variational Graph Auto-Encoders (VGAEs) have been widely used to solve the node clustering task. However, the state-of-the-art methods have numerous challenges. First, existing VGAEs do not account for the discrepancy between the inference and generative models after incorporating the clustering inductive bias. Second, current models are prone to degenerate solutions that make the latent codes match the prior independently of the input signal (i.e., Posterior Collapse). Third, existing VGAEs overlook the effect of the noisy clustering assignments (i.e., Feature Randomness) and the impact of the strong trade-off between clustering and reconstruction (i.e., Feature Drift). To address these problems, we formulate a variational lower bound in a contrastive setting. Our lower bound is a tighter approximation of the log-likelihood function than the corresponding Evidence Lower BOund (ELBO). Thanks to a newly identified term, our lower bound can escape Posterior Collapse and has more flexibility to account for the difference between the inference and generative models. Additionally, our solution has two mechanisms to control the trade-off between Feature Randomness and Feature Drift. Extensive experiments show that the proposed method achieves state-of-the-art clustering results on several datasets. We provide strong evidence that this improvement is attributed to four aspects: integrating contrastive learning and alleviating Feature Randomness, Feature Drift, and Posterior Collapse.
Audit logs are one of the most important tools for transparently tracking system events and maintaining continuous oversight in corporate organizations and enterprise business systems. There are many cases where the audit logs contain sensitive data, or the audit logs are enormous. In these situations, dealing with a subset of the data is more practical than the entire data set. To provide a secure solution to handle these issues, a sanitizable signature scheme (SSS) is a viable cryptographic primitive. Herein, we first present the \textit{first} post-quantum secure multivariate-based SSS, namely ${\sf Mul-SAN}$. Our proposed design provides unforgeability, privacy, immutability, signer accountability, and sanitizer accountability under the assumption that the $MQ$ problem is NP-hard. ${\sf Mul-SAN}$ is very efficient and only requires computing field multiplications and additions over a finite field for its implementation. ${\sf Mul-SAN}$ presents itself as a practical method to partially delegate control of the authenticated data in avenues like the healthcare industry and government organizations. We also explore using Blockchain to provide a tamper-proof and robust audit log mechanism.
Transformers have achieved promising results on a variety of tasks. However, the quadratic complexity in self-attention computation has limited the applications, especially in low-resource settings and mobile or edge devices. Existing works have proposed to exploit hand-crafted attention patterns to reduce computation complexity. However, such hand-crafted patterns are data-agnostic and may not be optimal. Hence, it is likely that relevant keys or values are being reduced, while less important ones are still preserved. Based on this key insight, we propose a novel deformable audio Transformer for audio recognition, named DATAR, where a deformable attention equipping with a pyramid transformer backbone is constructed and learnable. Such an architecture has been proven effective in prediction tasks,~\textit{e.g.}, event classification. Moreover, we identify that the deformable attention map computation may over-simplify the input feature, which can be further enhanced. Hence, we introduce a learnable input adaptor to alleviate this issue, and DATAR achieves state-of-the-art performance.
Vast amount of data generated from networks of sensors, wearables, and the Internet of Things (IoT) devices underscores the need for advanced modeling techniques that leverage the spatio-temporal structure of decentralized data due to the need for edge computation and licensing (data access) issues. While federated learning (FL) has emerged as a framework for model training without requiring direct data sharing and exchange, effectively modeling the complex spatio-temporal dependencies to improve forecasting capabilities still remains an open problem. On the other hand, state-of-the-art spatio-temporal forecasting models assume unfettered access to the data, neglecting constraints on data sharing. To bridge this gap, we propose a federated spatio-temporal model -- Cross-Node Federated Graph Neural Network (CNFGNN) -- which explicitly encodes the underlying graph structure using graph neural network (GNN)-based architecture under the constraint of cross-node federated learning, which requires that data in a network of nodes is generated locally on each node and remains decentralized. CNFGNN operates by disentangling the temporal dynamics modeling on devices and spatial dynamics on the server, utilizing alternating optimization to reduce the communication cost, facilitating computations on the edge devices. Experiments on the traffic flow forecasting task show that CNFGNN achieves the best forecasting performance in both transductive and inductive learning settings with no extra computation cost on edge devices, while incurring modest communication cost.
Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems. Most existing social recommendation models exploit pairwise relations to mine potential user preferences. However, real-life interactions among users are very complicated and user relations can be high-order. Hypergraph provides a natural way to model complex high-order relations, while its potentials for improving social recommendation are under-explored. In this paper, we fill this gap and propose a multi-channel hypergraph convolutional network to enhance social recommendation by leveraging high-order user relations. Technically, each channel in the network encodes a hypergraph that depicts a common high-order user relation pattern via hypergraph convolution. By aggregating the embeddings learned through multiple channels, we obtain comprehensive user representations to generate recommendation results. However, the aggregation operation might also obscure the inherent characteristics of different types of high-order connectivity information. To compensate for the aggregating loss, we innovatively integrate self-supervised learning into the training of the hypergraph convolutional network to regain the connectivity information with hierarchical mutual information maximization. The experimental results on multiple real-world datasets show that the proposed model outperforms the SOTA methods, and the ablation study verifies the effectiveness of the multi-channel setting and the self-supervised task. The implementation of our model is available via //github.com/Coder-Yu/RecQ.
Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for many applications: 1) the lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this work, we present an approach based on disentangled representation for producing diverse outputs without paired training images. To achieve diversity, we propose to embed images onto two spaces: a domain-invariant content space capturing shared information across domains and a domain-specific attribute space. Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time. To handle unpaired training data, we introduce a novel cross-cycle consistency loss based on disentangled representations. Qualitative results show that our model can generate diverse and realistic images on a wide range of tasks without paired training data. For quantitative comparisons, we measure realism with user study and diversity with a perceptual distance metric. We apply the proposed model to domain adaptation and show competitive performance when compared to the state-of-the-art on the MNIST-M and the LineMod datasets.
Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base. In this paper, we present a novel model called Interpretable Reasoning Network that employs an interpretable, hop-by-hop reasoning process for question answering. The model dynamically decides which part of an input question should be analyzed at each hop; predicts a relation that corresponds to the current parsed results; utilizes the predicted relation to update the question representation and the state of the reasoning process; and then drives the next-hop reasoning. Experiments show that our model yields state-of-the-art results on two datasets. More interestingly, the model can offer traceable and observable intermediate predictions for reasoning analysis and failure diagnosis, thereby allowing manual manipulation in predicting the final answer.
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