Differential privacy mechanisms such as the Gaussian or Laplace mechanism have been widely used in data analytics for preserving individual privacy. However, they are mostly designed for continuous outputs and are unsuitable for scenarios where discrete values are necessary. Although various quantization mechanisms were proposed recently to generate discrete outputs under differential privacy, the outcomes are either biased or have an inferior accuracy-privacy trade-off. In this paper, we propose a family of quantization mechanisms that is unbiased and differentially private. It has a high degree of freedom and we show that some existing mechanisms can be considered as special cases of ours. To find the optimal mechanism, we formulate a linear optimization that can be solved efficiently using linear programming tools. Experiments show that our proposed mechanism can attain a better privacy-accuracy trade-off compared to baselines.
Serving LLMs requires substantial memory due to the storage requirements of Key-Value (KV) embeddings in the KV cache, which grows with sequence length. An effective approach to compress KV cache is quantization. However, traditional quantization methods face significant memory overhead due to the need to store quantization constants (at least a zero point and a scale) in full precision per data block. Depending on the block size, this overhead can add 1 or 2 bits per quantized number. We introduce QJL, a new quantization approach that consists of a Johnson-Lindenstrauss (JL) transform followed by sign-bit quantization. In contrast to existing methods, QJL eliminates memory overheads by removing the need for storing quantization constants. We propose an asymmetric estimator for the inner product of two vectors and demonstrate that applying QJL to one vector and a standard JL transform without quantization to the other provides an unbiased estimator with minimal distortion. We have developed an efficient implementation of the QJL sketch and its corresponding inner product estimator, incorporating a lightweight CUDA kernel for optimized computation. When applied across various LLMs and NLP tasks to quantize the KV cache to only 3 bits, QJL demonstrates a more than fivefold reduction in KV cache memory usage without compromising accuracy, all while achieving faster runtime. Codes are available at \url{https://github.com/amirzandieh/QJL}.
Causal dynamics learning has recently emerged as a promising approach to enhancing robustness in reinforcement learning (RL). Typically, the goal is to build a dynamics model that makes predictions based on the causal relationships among the entities. Despite the fact that causal connections often manifest only under certain contexts, existing approaches overlook such fine-grained relationships and lack a detailed understanding of the dynamics. In this work, we propose a novel dynamics model that infers fine-grained causal structures and employs them for prediction, leading to improved robustness in RL. The key idea is to jointly learn the dynamics model with a discrete latent variable that quantizes the state-action space into subgroups. This leads to recognizing meaningful context that displays sparse dependencies, where causal structures are learned for each subgroup throughout the training. Experimental results demonstrate the robustness of our method to unseen states and locally spurious correlations in downstream tasks where fine-grained causal reasoning is crucial. We further illustrate the effectiveness of our subgroup-based approach with quantization in discovering fine-grained causal relationships compared to prior methods.
Quantization of large language models (LLMs) faces significant challenges, particularly due to the presence of outlier activations that impede efficient low-bit representation. Traditional approaches predominantly address Normal Outliers, which are activations across all tokens with relatively large magnitudes. However, these methods struggle with smoothing Massive Outliers that display significantly larger values, which leads to significant performance degradation in low-bit quantization. In this paper, we introduce DuQuant, a novel approach that utilizes rotation and permutation transformations to more effectively mitigate both massive and normal outliers. First, DuQuant starts by constructing the rotation matrix, using specific outlier dimensions as prior knowledge, to redistribute outliers to adjacent channels by block-wise rotation. Second, We further employ a zigzag permutation to balance the distribution of outliers across blocks, thereby reducing block-wise variance. A subsequent rotation further smooths the activation landscape, enhancing model performance. DuQuant simplifies the quantization process and excels in managing outliers, outperforming the state-of-the-art baselines across various sizes and types of LLMs on multiple tasks, even with 4-bit weight-activation quantization. Our code is available at https://github.com/Hsu1023/DuQuant.
Large language models (LLMs) have shown impressive capabilities across various tasks. However, training LLMs from scratch requires significant computational power and extensive memory capacity. Recent studies have explored low-rank structures on weights for efficient fine-tuning in terms of parameters and memory, either through low-rank adaptation or factorization. While effective for fine-tuning, low-rank structures are generally less suitable for pretraining because they restrict parameters to a low-dimensional subspace. In this work, we propose to parameterize the weights as a sum of low-rank and sparse matrices for pretraining, which we call SLTrain. The low-rank component is learned via matrix factorization, while for the sparse component, we employ a simple strategy of uniformly selecting the sparsity support at random and learning only the non-zero entries with the fixed support. While being simple, the random fixed-support sparse learning strategy significantly enhances pretraining when combined with low-rank learning. Our results show that SLTrain adds minimal extra parameters and memory costs compared to pretraining with low-rank parameterization, yet achieves substantially better performance, which is comparable to full-rank training. Remarkably, when combined with quantization and per-layer updates, SLTrain can reduce memory requirements by up to 73% when pretraining the LLaMA 7B model.
Unmanned underwater image analysis for marine monitoring faces two key challenges: (i) degraded image quality due to light attenuation and (ii) hardware storage constraints limiting high-resolution image collection. Existing methods primarily address image enhancement with approaches that hinge on storing the full-size input. In contrast, we introduce the Capsule Enhanced Variational AutoEncoder (CE-VAE), a novel architecture designed to efficiently compress and enhance degraded underwater images. Our attention-aware image encoder can project the input image onto a latent space representation while being able to run online on a remote device. The only information that needs to be stored on the device or sent to a beacon is a compressed representation. There is a dual-decoder module that performs offline, full-size enhanced image generation. One branch reconstructs spatial details from the compressed latent space, while the second branch utilizes a capsule-clustering layer to capture entity-level structures and complex spatial relationships. This parallel decoding strategy enables the model to balance fine-detail preservation with context-aware enhancements. CE-VAE achieves state-of-the-art performance in underwater image enhancement on six benchmark datasets, providing up to 3x higher compression efficiency than existing approaches. Code available at \url{https://github.com/iN1k1/ce-vae-underwater-image-enhancement}.
Diffusion transformers (DiTs) have exhibited remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, larger model sizes and multi-frame processing for video generation lead to increased computational and memory costs, posing challenges for practical deployment on edge devices. Post-Training Quantization (PTQ) is an effective method for reducing memory costs and computational complexity. When quantizing diffusion transformers, we find that applying existing diffusion quantization methods designed for U-Net faces challenges in preserving quality. After analyzing the major challenges for quantizing diffusion transformers, we design an improved quantization scheme: "ViDiT-Q": Video and Image Diffusion Transformer Quantization) to address these issues. Furthermore, we identify highly sensitive layers and timesteps hinder quantization for lower bit-widths. To tackle this, we improve ViDiT-Q with a novel metric-decoupled mixed-precision quantization method (ViDiT-Q-MP). We validate the effectiveness of ViDiT-Q across a variety of text-to-image and video models. While baseline quantization methods fail at W8A8 and produce unreadable content at W4A8, ViDiT-Q achieves lossless W8A8 quantization. ViDiTQ-MP achieves W4A8 with negligible visual quality degradation, resulting in a 2.5x memory optimization and a 1.5x latency speedup.
In this paper, we present a simple optimization-based preprocessing technique called Weight Magnitude Reduction (MagR) to improve the performance of post-training quantization. For each linear layer, we adjust the pre-trained floating-point weights by solving an $\ell_\infty$-regularized optimization problem. This process greatly diminishes the maximum magnitude of the weights and smooths out outliers, while preserving the layer's output. The preprocessed weights are centered more towards zero, which facilitates the subsequent quantization process. To implement MagR, we address the $\ell_\infty$-regularization by employing an efficient proximal gradient descent algorithm. Unlike existing preprocessing methods that involve linear transformations and subsequent post-processing steps, which can introduce significant overhead at inference time, MagR functions as a non-linear transformation, eliminating the need for any additional post-processing. This ensures that MagR introduces no overhead whatsoever during inference. Our experiments demonstrate that MagR achieves state-of-the-art performance on the Llama family of models. For example, we achieve a Wikitext2 perplexity of 5.95 on the LLaMA2-70B model for per-channel INT2 weight quantization without incurring any inference overhead.
Spatio-temporal compression of videos, utilizing networks such as Variational Autoencoders (VAE), plays a crucial role in OpenAI's SORA and numerous other video generative models. For instance, many LLM-like video models learn the distribution of discrete tokens derived from 3D VAEs within the VQVAE framework, while most diffusion-based video models capture the distribution of continuous latent extracted by 2D VAEs without quantization. The temporal compression is simply realized by uniform frame sampling which results in unsmooth motion between consecutive frames. Currently, there lacks of a commonly used continuous video (3D) VAE for latent diffusion-based video models in the research community. Moreover, since current diffusion-based approaches are often implemented using pre-trained text-to-image (T2I) models, directly training a video VAE without considering the compatibility with existing T2I models will result in a latent space gap between them, which will take huge computational resources for training to bridge the gap even with the T2I models as initialization. To address this issue, we propose a method for training a video VAE of latent video models, namely CV-VAE, whose latent space is compatible with that of a given image VAE, e.g., image VAE of Stable Diffusion (SD). The compatibility is achieved by the proposed novel latent space regularization, which involves formulating a regularization loss using the image VAE. Benefiting from the latent space compatibility, video models can be trained seamlessly from pre-trained T2I or video models in a truly spatio-temporally compressed latent space, rather than simply sampling video frames at equal intervals. With our CV-VAE, existing video models can generate four times more frames with minimal finetuning. Extensive experiments are conducted to demonstrate the effectiveness of the proposed video VAE.
Vision Transformers (ViTs) have excelled in computer vision tasks but are memory-consuming and computation-intensive, challenging their deployment on resource-constrained devices. To tackle this limitation, prior works have explored ViT-tailored quantization algorithms but retained floating-point scaling factors, which yield non-negligible re-quantization overhead, limiting ViTs' hardware efficiency and motivating more hardware-friendly solutions. To this end, we propose \emph{P$^2$-ViT}, the first \underline{P}ower-of-Two (PoT) \underline{p}ost-training quantization and acceleration framework to accelerate fully quantized ViTs. Specifically, {as for quantization,} we explore a dedicated quantization scheme to effectively quantize ViTs with PoT scaling factors, thus minimizing the re-quantization overhead. Furthermore, we propose coarse-to-fine automatic mixed-precision quantization to enable better accuracy-efficiency trade-offs. {In terms of hardware,} we develop {a dedicated chunk-based accelerator} featuring multiple tailored sub-processors to individually handle ViTs' different types of operations, alleviating reconfigurable overhead. Additionally, we design {a tailored row-stationary dataflow} to seize the pipeline processing opportunity introduced by our PoT scaling factors, thereby enhancing throughput. Extensive experiments consistently validate P$^2$-ViT's effectiveness. {Particularly, we offer comparable or even superior quantization performance with PoT scaling factors when compared to the counterpart with floating-point scaling factors. Besides, we achieve up to $\mathbf{10.1\times}$ speedup and $\mathbf{36.8\times}$ energy saving over GPU's Turing Tensor Cores, and up to $\mathbf{1.84\times}$ higher computation utilization efficiency against SOTA quantization-based ViT accelerators. Codes are available at \url{https://github.com/shihuihong214/P2-ViT}.
The prohibitive sizes of Large Language Models (LLMs) today make it difficult to deploy them on memory-constrained edge devices. This work introduces $\rm CALDERA$ -- a new post-training LLM compression algorithm that harnesses the inherent low-rank structure of a weight matrix $\mathbf{W}$ by approximating it via a low-rank, low-precision decomposition as $\mathbf{W} \approx \mathbf{Q} + \mathbf{L}\mathbf{R}$. Here, $\mathbf{L}$ and $\mathbf{R}$ are low rank factors, and the entries of $\mathbf{Q}$, $\mathbf{L}$ and $\mathbf{R}$ are quantized. The model is compressed by substituting each layer with its $\mathbf{Q} + \mathbf{L}\mathbf{R}$ decomposition, and the zero-shot performance of the compressed model is evaluated. Additionally, $\mathbf{L}$ and $\mathbf{R}$ are readily amenable to low-rank adaptation, consequently enhancing the zero-shot performance. $\rm CALDERA$ obtains this decomposition by formulating it as an optimization problem $\min_{\mathbf{Q},\mathbf{L},\mathbf{R}}\lVert(\mathbf{Q} + \mathbf{L}\mathbf{R} - \mathbf{W})\mathbf{X}^\top\rVert_{\rm F}^2$, where $\mathbf{X}$ is the calibration data, and $\mathbf{Q}, \mathbf{L}, \mathbf{R}$ are constrained to be representable using low-precision formats. Theoretical upper bounds on the approximation error of $\rm CALDERA$ are established using a rank-constrained regression framework, and the tradeoff between compression ratio and model performance is studied by analyzing the impact of target rank and quantization bit budget. Results illustrate that compressing LlaMa-$2$ $7$B/$13B$/$70$B and LlaMa-$3$ $8$B models using $\rm CALDERA$ outperforms existing post-training LLM compression techniques in the regime of less than $2.5$ bits per parameter. The implementation is available at: https://github.com/pilancilab/caldera.
Sequential Recommendation (SR) task involves predicting the next item a user is likely to interact with, given their past interactions. The SR models examine the sequence of a user's actions to discern more complex behavioral patterns and temporal dynamics. Recent research demonstrates the great impact of LLMs on sequential recommendation systems, either viewing sequential recommendation as language modeling or serving as the backbone for user representation. Although these methods deliver outstanding performance, there is scant evidence of the necessity of a large language model and how large the language model is needed, especially in the sequential recommendation scene. Meanwhile, due to the huge size of LLMs, it is inefficient and impractical to apply a LLM-based model in real-world platforms that often need to process billions of traffic logs daily. In this paper, we explore the influence of LLMs' depth by conducting extensive experiments on large-scale industry datasets. Surprisingly, our motivational experiments reveal that most intermediate layers of LLMs are redundant, indicating that pruning the remaining layers can still maintain strong performance. Motivated by this insight, we empower small language models for SR, namely SLMRec, which adopt a simple yet effective knowledge distillation method. Moreover, SLMRec is orthogonal to other post-training efficiency techniques, such as quantization and pruning, so that they can be leveraged in combination. Comprehensive experimental results illustrate that the proposed SLMRec model attains the best performance using only 13% of the parameters found in LLM-based recommendation models while simultaneously achieving up to 6.6x and 8.0x speedups in training and inference time costs, respectively. Besides, we provide a theoretical justification for why small language models can perform comparably to large language models in SR.
Second-order optimizers, maintaining a matrix termed a preconditioner, are superior to first-order optimizers in both theory and practice. The states forming the preconditioner and its inverse root restrict the maximum size of models trained by second-order optimizers. To address this, compressing 32-bit optimizer states to lower bitwidths has shown promise in reducing memory usage. However, current approaches only pertain to first-order optimizers. In this paper, we propose the first 4-bit second-order optimizers, exemplified by 4-bit Shampoo, maintaining performance similar to that of 32-bit ones. We show that quantizing the eigenvector matrix of the preconditioner in 4-bit Shampoo is remarkably better than quantizing the preconditioner itself both theoretically and experimentally. By rectifying the orthogonality of the quantized eigenvector matrix, we enhance the approximation of the preconditioner's eigenvector matrix, which also benefits the computation of its inverse 4-th root. Besides, we find that linear square quantization slightly outperforms dynamic tree quantization when quantizing second-order optimizer states. Evaluation on various networks for image classification and natural language modeling demonstrates that our 4-bit Shampoo achieves comparable performance to its 32-bit counterpart while being more memory-efficient.
Quantization leverages lower-precision weights to reduce the memory usage of large language models (LLMs) and is a key technique for enabling their deployment on commodity hardware. While LLM quantization's impact on utility has been extensively explored, this work for the first time studies its adverse effects from a security perspective. We reveal that widely used quantization methods can be exploited to produce a harmful quantized LLM, even though the full-precision counterpart appears benign, potentially tricking users into deploying the malicious quantized model. We demonstrate this threat using a three-staged attack framework: (i) first, we obtain a malicious LLM through fine-tuning on an adversarial task; (ii) next, we quantize the malicious model and calculate constraints that characterize all full-precision models that map to the same quantized model; (iii) finally, using projected gradient descent, we tune out the poisoned behavior from the full-precision model while ensuring that its weights satisfy the constraints computed in step (ii). This procedure results in an LLM that exhibits benign behavior in full precision but when quantized, it follows the adversarial behavior injected in step (i). We experimentally demonstrate the feasibility and severity of such an attack across three diverse scenarios: vulnerable code generation, content injection, and over-refusal attack. In practice, the adversary could host the resulting full-precision model on an LLM community hub such as Hugging Face, exposing millions of users to the threat of deploying its malicious quantized version on their devices.
Despite advances using low-rank adapters and quantization, pretraining of large models on consumer hardware has not been possible without model sharding, offloading during training, or per-layer gradient updates. To address these limitations, we propose Low-Rank Adapters for Quantized Training (LoQT), a method for efficiently training quantized models. LoQT uses gradient-based tensor factorization to initialize low-rank trainable weight matrices that are periodically merged into quantized full-rank weight matrices. Our approach is suitable for both pretraining and fine-tuning models. We demonstrate this for language modeling and downstream task adaptation, finding that LoQT enables efficient training of models up to 7B parameters on a 24GB GPU. We also demonstrate the feasibility of training a 13B model using per-layer gradient updates on the same hardware.
We present a novel end-to-end framework that generates highly compact (typically 6-15 dimensions), discrete (int4 type), and interpretable node representations, termed node identifiers (node IDs), to tackle inference challenges on large-scale graphs. By employing vector quantization, we compress continuous node embeddings from multiple layers of a Graph Neural Network (GNN) into discrete codes, applicable under both self-supervised and supervised learning paradigms. These node IDs capture high-level abstractions of graph data and offer interpretability that traditional GNN embeddings lack. Extensive experiments on 34 datasets, encompassing node classification, graph classification, link prediction, and attributed graph clustering tasks, demonstrate that the generated node IDs significantly enhance speed and memory efficiency while achieving competitive performance compared to current state-of-the-art methods.
This paper presents M$^3$GPT, an advanced $\textbf{M}$ultimodal, $\textbf{M}$ultitask framework for $\textbf{M}$otion comprehension and generation. M$^3$GPT operates on three fundamental principles. The first focuses on creating a unified representation space for various motion-relevant modalities. We employ discrete vector quantization for multimodal conditional signals, such as text, music and motion/dance, enabling seamless integration into a large language model (LLM) with a single vocabulary. The second involves modeling motion generation directly in the raw motion space. This strategy circumvents the information loss associated with a discrete tokenizer, resulting in more detailed and comprehensive motion generation. Third, M$^3$GPT learns to model the connections and synergies among various motion-relevant tasks. Text, the most familiar and well-understood modality for LLMs, is utilized as a bridge to establish connections between different motion tasks, facilitating mutual reinforcement. To our knowledge, M$^3$GPT is the first model capable of comprehending and generating motions based on multiple signals. Extensive experiments highlight M$^3$GPT's superior performance across various motion-relevant tasks and its powerful zero-shot generalization capabilities for extremely challenging tasks. Project page: \url{https://github.com/luomingshuang/M3GPT}.
The recent introduction of Diffusion Transformers (DiTs) has demonstrated exceptional capabilities in image generation by using a different backbone architecture, departing from traditional U-Nets and embracing the scalable nature of transformers. Despite their advanced capabilities, the wide deployment of DiTs, particularly for real-time applications, is currently hampered by considerable computational demands at the inference stage. Post-training Quantization (PTQ) has emerged as a fast and data-efficient solution that can significantly reduce computation and memory footprint by using low-bit weights and activations. However, its applicability to DiTs has not yet been explored and faces non-trivial difficulties due to the unique design of DiTs. In this paper, we propose PTQ4DiT, a specifically designed PTQ method for DiTs. We discover two primary quantization challenges inherent in DiTs, notably the presence of salient channels with extreme magnitudes and the temporal variability in distributions of salient activation over multiple timesteps. To tackle these challenges, we propose Channel-wise Salience Balancing (CSB) and Spearmen's $\rho$-guided Salience Calibration (SSC). CSB leverages the complementarity property of channel magnitudes to redistribute the extremes, alleviating quantization errors for both activations and weights. SSC extends this approach by dynamically adjusting the balanced salience to capture the temporal variations in activation. Additionally, to eliminate extra computational costs caused by PTQ4DiT during inference, we design an offline re-parameterization strategy for DiTs. Experiments demonstrate that our PTQ4DiT successfully quantizes DiTs to 8-bit precision (W8A8) while preserving comparable generation ability and further enables effective quantization to 4-bit weight precision (W4A8) for the first time.
Large language models (LLMs) achieve remarkable performance in natural language understanding but require substantial computation and memory resources. Post-training quantization (PTQ) is a powerful compression technique extensively investigated in LLMs. However, existing PTQ methods are still not ideal in terms of accuracy and efficiency, especially with below 4 bit-widths. Standard PTQ methods using group-wise quantization suffer difficulties in quantizing LLMs accurately to such low-bit, but advanced methods remaining high-precision weights element-wisely are hard to realize their theoretical hardware efficiency. This paper presents a Salience-Driven Mixed-Precision Quantization scheme for LLMs, namely SliM-LLM. The scheme exploits the salience distribution of weights to determine optimal bit-width and quantizers for accurate LLM quantization, while aligning bit-width partition to groups for compact memory usage and fast integer inference. Specifically, the proposed SliM-LLM mainly relies on two novel techniques: (1) Salience-Determined Bit Allocation utilizes the clustering characteristics of salience distribution to allocate the bit-widths of each group, increasing the accuracy of quantized LLMs and maintaining the inference efficiency; (2) Salience-Weighted Quantizer Calibration optimizes the parameters of the quantizer by considering the element-wise salience within the group, balancing the maintenance of salient information and minimization of errors. Comprehensive experiments show that SliM-LLM significantly improves the accuracy of LLMs at ultra-low bits, e.g., 2-bit LLaMA-7B achieves a 5.5-times memory-saving than original model on NVIDIA A800 GPUs, and 48% decrease of perplexity compared to the state-of-the-art gradient-free PTQ method. Moreover, SliM-LLM+, which is integrated from the extension of SliM-LLM with gradient-based quantizers, further reduces perplexity by 35.1%.
This paper presents a novel approach to enhance communication efficiency in federated learning through clipped uniform quantization. By leveraging optimal clipping thresholds and client-specific adaptive quantization schemes, the proposed method significantly reduces bandwidth and memory requirements for model weight transmission between clients and the server while maintaining competitive accuracy. We investigate the effects of symmetric clipping and uniform quantization on model performance, emphasizing the role of stochastic quantization in mitigating artifacts and improving robustness. Extensive simulations demonstrate that the method achieves near-full-precision performance with substantial communication savings. Moreover, the proposed approach facilitates efficient weight averaging based on the inverse of the mean squared quantization errors, effectively balancing the trade-off between communication efficiency and model accuracy. Moreover, in contrast to federated averaging, this design obviates the need to disclose client-specific data volumes to the server, thereby enhancing client privacy. Comparative analysis with conventional quantization methods further confirms the efficacy of the proposed scheme.