Vector quantization-based image semantic communication systems have successfully boosted transmission efficiency, but face challenges with conflicting requirements between codebook design and digital constellation modulation. Traditional codebooks need wide index ranges, while modulation favors few discrete states. To address this, we propose a multilevel generative semantic communication system with a two-stage training framework. In the first stage, we train a high-quality codebook, using a multi-head octonary codebook (MOC) to compress the index range. In addition, a residual vector quantization (RVQ) mechanism is also integrated for effective multilevel communication. In the second stage, a noise reduction block (NRB) based on Swin Transformer is introduced, coupled with the multilevel codebook from the first stage, serving as a high-quality semantic knowledge base (SKB) for generative feature restoration. Finally, to simulate modern image transmission scenarios, we employ a diverse collection of high-resolution 2K images as the test set. The experimental results consistently demonstrate the superior performance of MOC-RVQ over conventional methods such as BPG or JPEG. Additionally, MOC-RVQ achieves comparable performance to an analog JSCC scheme, while needing only one-sixth of the channel bandwidth ratio (CBR) and being directly compatible with digital transmission systems.
Vector quantization (VQ) is a technique to deterministically learn features with discrete codebook representations. It is commonly performed with a variational autoencoding model, VQ-VAE, which can be further extended to hierarchical structures for making high-fidelity reconstructions. However, such hierarchical extensions of VQ-VAE often suffer from the codebook/layer collapse issue, where the codebook is not efficiently used to express the data, and hence degrades reconstruction accuracy. To mitigate this problem, we propose a novel unified framework to stochastically learn hierarchical discrete representation on the basis of the variational Bayes framework, called hierarchically quantized variational autoencoder (HQ-VAE). HQ-VAE naturally generalizes the hierarchical variants of VQ-VAE, such as VQ-VAE-2 and residual-quantized VAE (RQ-VAE), and provides them with a Bayesian training scheme. Our comprehensive experiments on image datasets show that HQ-VAE enhances codebook usage and improves reconstruction performance. We also validated HQ-VAE in terms of its applicability to a different modality with an audio dataset.
Modern deep learning models have the ability to generate high-dimensional vectors whose similarity reflects semantic resemblance. Thus, similarity search, i.e., the operation of retrieving those vectors in a large collection that are similar to a given query, has become a critical component of a wide range of applications that demand highly accurate and timely answers. In this setting, the high vector dimensionality puts similarity search systems under compute and memory pressure, leading to subpar performance. Additionally, cross-modal retrieval tasks have become increasingly common, e.g., where a user inputs a text query to find the most relevant images for that query. However, these queries often have different distributions than the database embeddings, making it challenging to achieve high accuracy. In this work, we present LeanVec, a framework that combines linear dimensionality reduction with vector quantization to accelerate similarity search on high-dimensional vectors while maintaining accuracy. We present LeanVec variants for in-distribution (ID) and out-of-distribution (OOD) queries. LeanVec-ID yields accuracies on par with those from recently introduced deep learning alternatives whose computational overhead precludes their usage in practice. LeanVec-OOD uses two novel techniques for dimensionality reduction that consider the query and database distributions to simultaneously boost the accuracy and the performance of the framework even further (even presenting competitive results when the query and database distributions match). All in all, our extensive and varied experimental results show that LeanVec produces state-of-the-art results, with up to 3.7x improvement in search throughput and up to 4.9x faster index build time over the state of the art.
In recent years, multimodal large language models (MLLMs) such as GPT-4V have demonstrated remarkable advancements, excelling in a variety of vision-language tasks. Despite their prowess, the closed-source nature and computational demands of such models limit their accessibility and applicability. This study introduces TinyGPT-V, a novel open-source MLLM, designed for efficient training and inference across various vision-language tasks, including image captioning (IC) and visual question answering (VQA). Leveraging a compact yet powerful architecture, TinyGPT-V integrates the Phi-2 language model with pre-trained vision encoders, utilizing a unique mapping module for visual and linguistic information fusion. With a training regimen optimized for small backbones and employing a diverse dataset amalgam, TinyGPT-V requires significantly lower computational resources 24GB for training and as little as 8GB for inference without compromising on performance. Our experiments demonstrate that TinyGPT-V, with its language model 2.8 billion parameters, achieves comparable results in VQA and image inference tasks to its larger counterparts while being uniquely suited for deployment on resource-constrained devices through innovative quantization techniques. This work not only paves the way for more accessible and efficient MLLMs but also underscores the potential of smaller, optimized models in bridging the gap between high performance and computational efficiency in real-world applications. Additionally, this paper introduces a new approach to multimodal large language models using smaller backbones. Our code and training weights are available in the supplementary material.
Neural graphics primitives are faster and achieve higher quality when their neural networks are augmented by spatial data structures that hold trainable features arranged in a grid. However, existing feature grids either come with a large memory footprint (dense or factorized grids, trees, and hash tables) or slow performance (index learning and vector quantization). In this paper, we show that a hash table with learned probes has neither disadvantage, resulting in a favorable combination of size and speed. Inference is faster than unprobed hash tables at equal quality while training is only 1.2-2.6x slower, significantly outperforming prior index learning approaches. We arrive at this formulation by casting all feature grids into a common framework: they each correspond to a lookup function that indexes into a table of feature vectors. In this framework, the lookup functions of existing data structures can be combined by simple arithmetic combinations of their indices, resulting in Pareto optimal compression and speed.
With the widespread adoption of Large Language Models (LLMs), many deep learning practitioners are looking for strategies of running these models more efficiently. One such strategy is to use sparse Mixture-of-Experts (MoE) - a type of model architectures where only a fraction of model layers are active for any given input. This property allows MoE-based language models to generate tokens faster than their dense counterparts, but it also increases model size due to having multiple experts. Unfortunately, this makes state-of-the-art MoE language models difficult to run without high-end GPUs. In this work, we study the problem of running large MoE language models on consumer hardware with limited accelerator memory. We build upon parameter offloading algorithms and propose a novel strategy that accelerates offloading by taking advantage of innate properties of MoE LLMs. Using this strategy, we build can run Mixtral-8x7B with mixed quantization on desktop hardware and free-tier Google Colab instances.
Graph Neural Network (GNN) ushered in a new era of machine learning with interconnected datasets. While traditional neural networks can only be trained on independent samples, GNN allows for the inclusion of inter-sample interactions in the training process. This gain, however, incurs additional memory cost, rendering most GNNs unscalable for real-world applications involving vast and complicated networks with tens of millions of nodes (e.g., social circles, web graphs, and brain graphs). This means that storing the graph in the main memory can be difficult, let alone training the GNN model with significantly less GPU memory. While much of the recent literature has focused on either mini-batching GNN methods or quantization, graph reduction methods remain largely scarce. Furthermore, present graph reduction approaches have several drawbacks. First, most graph reduction focuses only on the inference stage (e.g., condensation and distillation) and requires full graph GNN training, which does not reduce training memory footprint. Second, many methods focus solely on the graph's structural aspect, ignoring the initial population feature-label distribution, resulting in a skewed post-reduction label distribution. Here, we propose a Feature-Label COnstrained graph Net collapse, FALCON, to address these limitations. Our three core contributions lie in (i) designing FALCON, a topology-aware graph reduction technique that preserves feature-label distribution; (ii) implementation of FALCON with other memory reduction methods (i.e., mini-batched GNN and quantization) for further memory reduction; (iii) extensive benchmarking and ablation studies against SOTA methods to evaluate FALCON memory reduction. Our extensive results show that FALCON can significantly collapse various public datasets while achieving equal prediction quality across GNN models. Code: https://github.com/basiralab/FALCON
Effective communication protocols in multi-agent reinforcement learning (MARL) are critical to fostering cooperation and enhancing team performance. To leverage communication, many previous works have proposed to compress local information into a single message and broadcast it to all reachable agents. This simplistic messaging mechanism, however, may fail to provide adequate, critical, and relevant information to individual agents, especially in severely bandwidth-limited scenarios. This motivates us to develop context-aware communication schemes for MARL, aiming to deliver personalized messages to different agents. Our communication protocol, named CACOM, consists of two stages. In the first stage, agents exchange coarse representations in a broadcast fashion, providing context for the second stage. Following this, agents utilize attention mechanisms in the second stage to selectively generate messages personalized for the receivers. Furthermore, we employ the learned step size quantization (LSQ) technique for message quantization to reduce the communication overhead. To evaluate the effectiveness of CACOM, we integrate it with both actor-critic and value-based MARL algorithms. Empirical results on cooperative benchmark tasks demonstrate that CACOM provides evident performance gains over baselines under communication-constrained scenarios. The code is publicly available at https://github.com/LXXXXR/CACOM.
Deep Neural Networks (DNNs) have shown significant advantages in a wide variety of domains. However, DNNs are becoming computationally intensive and energy hungry at an exponential pace, while at the same time, there is a vast demand for running sophisticated DNN-based services on resource constrained embedded devices. In this paper, we target energy-efficient inference on embedded DNN accelerators. To that end, we propose an automated framework to compress DNNs in a hardware-aware manner by jointly employing pruning and quantization. We explore, for the first time, per-layer fine- and coarse-grained pruning, in the same DNN architecture, in addition to low bit-width mixed-precision quantization for weights and activations. Reinforcement Learning (RL) is used to explore the associated design space and identify the pruning-quantization configuration so that the energy consumption is minimized whilst the prediction accuracy loss is retained at acceptable levels. Using our novel composite RL agent we are able to extract energy-efficient solutions without requiring retraining and/or fine tuning. Our extensive experimental evaluation over widely used DNNs and the CIFAR-10/100 and ImageNet datasets demonstrates that our framework achieves $39\%$ average energy reduction for $1.7\%$ average accuracy loss and outperforms significantly the state-of-the-art approaches.
The Stable Diffusion Model (SDM) is a popular and efficient text-to-image (t2i) generation and image-to-image (i2i) generation model. Although there have been some attempts to reduce sampling steps, model distillation, and network quantization, these previous methods generally retain the original network architecture. Billion scale parameters and high computing requirements make the research of model architecture adjustment scarce. In this work, we first explore the computational redundancy part of the network, and then prune the redundancy blocks of the model and maintain the network performance through a progressive incubation strategy. Secondly, in order to maintaining the model performance, we add cross-layer multi-expert conditional convolution (CLME-Condconv) to the block pruning part to inherit the original convolution parameters. Thirdly, we propose a global-regional interactive (GRI) attention to speed up the computationally intensive attention part. Finally, we use semantic-aware supervision (SAS) to align the outputs of the teacher model and student model at the semantic level. Experiments show that this method can effectively train a lightweight model close to the performance of the original SD model, and effectively improve the model speed under limited resources. Experiments show that the proposed method can effectively train a light-weight model close to the performance of the original SD model, and effectively improve the model speed under limited resources. After acceleration, the UNet part of the model is 22% faster and the overall speed is 19% faster.
While data is distributed in multiple edge devices, Federated Learning (FL) is attracting more and more attention to collaboratively train a machine learning model without transferring raw data. FL generally exploits a parameter server and a large number of edge devices during the whole process of the model training, while several devices are selected in each round. However, straggler devices may slow down the training process or even make the system crash during training. Meanwhile, other idle edge devices remain unused. As the bandwidth between the devices and the server is relatively low, the communication of intermediate data becomes a bottleneck. In this paper, we propose Time-Efficient Asynchronous federated learning with Sparsification and Quantization, i.e., TEASQ-Fed. TEASQ-Fed can fully exploit edge devices to asynchronously participate in the training process by actively applying for tasks. We utilize control parameters to choose an appropriate number of parallel edge devices, which simultaneously execute the training tasks. In addition, we introduce a caching mechanism and weighted averaging with respect to model staleness to further improve the accuracy. Furthermore, we propose a sparsification and quantitation approach to compress the intermediate data to accelerate the training. The experimental results reveal that TEASQ-Fed improves the accuracy (up to 16.67% higher) while accelerating the convergence of model training (up to twice faster).
Deep neural networks are characterized by multiple symmetrical, equi-loss solutions that are redundant. Thus, the order of neurons in a layer and feature maps can be given arbitrary permutations, without affecting (or minimally affecting) their output. If we shuffle these neurons, or if we apply to them some perturbations (like fine-tuning) can we put them back in the original order i.e. re-synchronize? Is there a possible corruption threat? Answering these questions is important for applications like neural network white-box watermarking for ownership tracking and integrity verification. We advance a method to re-synchronize the order of permuted neurons. Our method is also effective if neurons are further altered by parameter pruning, quantization, and fine-tuning, showing robustness to integrity attacks. Additionally, we provide theoretical and practical evidence for the usual means to corrupt the integrity of the model, resulting in a solution to counter it. We test our approach on popular computer vision datasets and models, and we illustrate the threat and our countermeasure on a popular white-box watermarking method.
Motivated by high resource costs of centralized machine learning schemes as well as data privacy concerns, federated learning (FL) emerged as an efficient alternative that relies on aggregating locally trained models rather than collecting clients' potentially private data. In practice, available resources and data distributions vary from one client to another, creating an inherent system heterogeneity that leads to deterioration of the performance of conventional FL algorithms. In this work, we present a federated quantization-based self-supervised learning scheme (Fed-QSSL) designed to address heterogeneity in FL systems. At clients' side, to tackle data heterogeneity we leverage distributed self-supervised learning while utilizing low-bit quantization to satisfy constraints imposed by local infrastructure and limited communication resources. At server's side, Fed-QSSL deploys de-quantization, weighted aggregation and re-quantization, ultimately creating models personalized to both data distribution as well as specific infrastructure of each client's device. We validated the proposed algorithm on real world datasets, demonstrating its efficacy, and theoretically analyzed impact of low-bit training on the convergence and robustness of the learned models.
3D Gaussian Splatting has recently emerged as a highly promising technique for modeling of static 3D scenes. In contrast to Neural Radiance Fields, it utilizes efficient rasterization allowing for very fast rendering at high-quality. However, the storage size is significantly higher, which hinders practical deployment, e.g. on resource constrained devices. In this paper, we introduce a compact scene representation organizing the parameters of 3D Gaussian Splatting (3DGS) into a 2D grid with local homogeneity, ensuring a drastic reduction in storage requirements without compromising visual quality during rendering. Central to our idea is the explicit exploitation of perceptual redundancies present in natural scenes. In essence, the inherent nature of a scene allows for numerous permutations of Gaussian parameters to equivalently represent it. To this end, we propose a novel highly parallel algorithm that regularly arranges the high-dimensional Gaussian parameters into a 2D grid while preserving their neighborhood structure. During training, we further enforce local smoothness between the sorted parameters in the grid. The uncompressed Gaussians use the same structure as 3DGS, ensuring a seamless integration with established renderers. Our method achieves a reduction factor of 17x to 42x in size for complex scenes with no increase in training time, marking a substantial leap forward in the domain of 3D scene distribution and consumption. Additional information can be found on our project page: https://fraunhoferhhi.github.io/Self-Organizing-Gaussians/
Recently segment anything model (SAM) has shown powerful segmentation capability and has drawn great attention in computer vision fields. Massive following works have developed various applications based on the pre-trained SAM and achieved impressive performance on downstream vision tasks. However, SAM consists of heavy architectures and requires massive computational capacity, which hinders the further application of SAM on computation constrained edge devices. To this end, in this paper we propose a framework to obtain a tiny segment anything model (TinySAM) while maintaining the strong zero-shot performance. We first propose a full-stage knowledge distillation method with hard prompt sampling and hard mask weighting strategy to distill a lightweight student model. We also adapt the post-training quantization to the prompt-based segmentation task and further reduce the computational cost. Moreover, a hierarchical segmenting everything strategy is proposed to accelerate the everything inference by $2\times$ with almost no performance degradation. With all these proposed methods, our TinySAM leads to orders of magnitude computational reduction and pushes the envelope for efficient segment anything task. Extensive experiments on various zero-shot transfer tasks demonstrate the significantly advantageous performance of our TinySAM against counterpart methods. Codes are available at https://github.com/xinghaochen/TinySAM and https://gitee.com/mindspore/models/tree/master/research/cv/TinySAM.
Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics. Since deep learning is known to be computing- and memory-intensive, traditional fault-tolerant approaches based on redundant computing will incur substantial overhead including power consumption and chip area. To this end, we propose to characterize deep learning vulnerability difference across both neurons and bits of each neuron, and leverage the vulnerability difference to enable selective protection of the deep learning processing components from the perspective of architecture layer and circuit layer respectively. At the same time, we observe the correlation between model quantization and bit protection overhead of the underlying processing elements of deep learning accelerators, and propose to reduce the bit protection overhead by adding additional quantization constrain without compromising the model accuracy. Finally, we employ Bayesian optimization strategy to co-optimize the correlated cross-layer design parameters at algorithm layer, architecture layer, and circuit layer to minimize the hardware resource consumption while fulfilling multiple user constraints including reliability, accuracy, and performance of the deep learning processing at the same time.
Recent one-shot Neural Architecture Search algorithms rely on training a hardware-agnostic super-network tailored to a specific task and then extracting efficient sub-networks for different hardware platforms. Popular approaches separate the training of super-networks from the search for sub-networks, often employing predictors to alleviate the computational overhead associated with search. Additionally, certain methods also incorporate the quantization policy within the search space. However, while the quantization policy search for convolutional neural networks is well studied, the extension of these methods to transformers and especially foundation models remains under-explored. In this paper, we demonstrate that by using multi-objective search algorithms paired with lightly trained predictors, we can efficiently search for both the sub-network architecture and the corresponding quantization policy and outperform their respective baselines across different performance objectives such as accuracy, model size, and latency. Specifically, we demonstrate that our approach performs well across both uni-modal (ViT and BERT) and multi-modal (BEiT-3) transformer-based architectures as well as convolutional architectures (ResNet). For certain networks, we demonstrate an improvement of up to $4.80x$ and $3.44x$ for latency and model size respectively, without degradation in accuracy compared to the fully quantized INT8 baselines.
Learned image compression has a problem of non-bit-exact reconstruction due to different calculations of floating point arithmetic on different devices. This paper shows a method to achieve a deterministic reconstructed image by quantizing only the decoder of the learned image compression model. From the implementation perspective of an image codec, it is beneficial to have the results reproducible when decoded on different devices. In this paper, we study quantization of weights and activations without overflow of accumulator in all decoder subnetworks. We show that the results are bit-exact at the output, and the resulting BD-rate loss of quantization of decoder is 0.5 % in the case of 16-bit weights and 16-bit activations, and 7.9 % in the case of 8-bit weights and 16-bit activations.
Analog-to-digital converters (ADCs) facilitate the conversion of analog signals into a digital format. While the specific designs and settings of ADCs can vary depending on their applications, it is crucial in many modern applications to minimize their power consumption. The significance of low-power ADCs is particularly evident in fields like mobile and handheld devices reliant on battery operation. Key parameters of the ADCs that dictate the ADC's power are its sampling rate, dynamic range, and number of quantization bits. Typically, these parameters are required to be higher than a threshold value but can be reduced by using the structure of the signal and by leveraging preprocessing and the system application needs. In this review, we discuss four approaches relevant to a variety of applications.
In AI research, the optimization of Large Language Models (LLMs) remains a significant challenge, crucial for advancing the field's practical applications and sustainability. Building upon the foundational work of Professor Song Han's lab at MIT, this paper introduces a novel approach in developing Mini-GPTs via contextual pruning. Our methodology strategically prunes the computational architecture of traditional LLMs, like Phi-1.5, focusing on retaining core functionalities while drastically reducing model sizes. We employ the technique across diverse and complex datasets, including US law, Medical Q&A, Skyrim dialogue, English-Taiwanese translation, and Economics articles. The results underscore the efficiency and effectiveness of contextual pruning, not merely as a theoretical concept but as a practical tool in developing domain-specific, resource-efficient LLMs. Contextual pruning is a promising method for building domain-specific LLMs, and this research is a building block towards future development with more hardware compute, refined fine-tuning, and quantization.