Yao Shu

Yao Shu, Wenyang Hu, See-Kiong Ng et al.

Large Language Models (LLMs) have become indispensable in numerous real-world applications. However, fine-tuning these models at scale, especially in federated settings where data privacy and communication efficiency are critical, presents significant challenges. Existing approaches often resort to parameter-efficient fine-tuning (PEFT) to mitigate communication overhead, but this typically comes at the cost of model accuracy. To this end, we propose federated full-parameter tuning at scale for LLMs (Ferret), the first first-order method with shared randomness to enable scalable full-parameter tuning of LLMs across decentralized data sources while maintaining competitive model accuracy. Ferret accomplishes this through three aspects: (i) it employs widely used first-order methods for efficient local updates; (ii) it projects these updates into a low-dimensional space to considerably reduce communication overhead; and (iii) it reconstructs local updates from this low-dimensional space with shared randomness to facilitate effective full-parameter global aggregation, ensuring fast convergence and competitive final performance. Our rigorous theoretical analyses and insights along with extensive experiments, show that Ferret significantly enhances the scalability of existing federated full-parameter tuning approaches by achieving high computational efficiency, reduced communication overhead, and fast convergence, all while maintaining competitive model accuracy. Our implementation is available at https://github.com/allen4747/Ferret.

Yao Shu, Xiaoqiang Lin, Zhongxiang Dai et al.

Federated optimization, an emerging paradigm which finds wide real-world applications such as federated learning, enables multiple clients (e.g., edge devices) to collaboratively optimize a global function. The clients do not share their local datasets and typically only share their local gradients. However, the gradient information is not available in many applications of federated optimization, which hence gives rise to the paradigm of federated zeroth-order optimization (ZOO). Existing federated ZOO algorithms suffer from the limitations of query and communication inefficiency, which can be attributed to (a) their reliance on a substantial number of function queries for gradient estimation and (b) the significant disparity between their realized local updates and the intended global updates. To this end, we (a) introduce trajectory-informed gradient surrogates which is able to use the history of function queries during optimization for accurate and query-efficient gradient estimation, and (b) develop the technique of adaptive gradient correction using these gradient surrogates to mitigate the aforementioned disparity. Based on these, we propose the federated zeroth-order optimization using trajectory-informed surrogate gradients (FZooS) algorithm for query- and communication-efficient federated ZOO. Our FZooS achieves theoretical improvements over the existing approaches, which is supported by our real-world experiments such as federated black-box adversarial attack and federated non-differentiable metric optimization.

Chenxing Wei, Yao Shu, Ying Tiffany He et al.

Large Language Models (LLMs) are driving advancements in artificial intelligence by increasing the scale of model parameters, which has significantly enhanced generalization ability and unlocked new capabilities in practice. However, their performance in specific downstream tasks is usually hindered by their knowledge boundaries on these tasks. Thus, fine-tuning techniques, especially the widely used Low-Rank Adaptation (LoRA) method, have been introduced to expand the boundaries on these tasks, whereas LoRA would underperform on certain tasks owing to its potential overfitting on these tasks. To overcome this overfitting and improve the performance of LoRA, we propose the flexible low rank adaptation (Flexora) method to automatically and flexibly select the most important layers needing to be fine-tuned to achieve the best performance on different downstream tasks. Specifically, Flexora firstly frames this layer selection problem as a well-defined hyperparameter optimization (HPO) problem, then addresses it using the unrolled differentiation (UD) method, and finally selects the most useful layers based on the optimized hyperparameters. Our extensive experiments on many pretrained models and natural language tasks show that Flexora is able to consistently improve over the existing baselines, indicating the effectiveness of our Flexora in practice. We additionally provide insightful theoretical results and many ablation studies to deliver a comprehensive understanding of our Flexora.

Yunwei Bai, Ying Kiat Tan, Yao Shu et al.

Few-shot learning (FSL) challenges model generalization to novel classes based on just a few shots of labeled examples, a testbed where traditional test-time augmentations fail to be effective. We introduce 1S-DAug, a one-shot generative augmentation operator that synthesizes diverse yet faithful variants from just one example image at test time. 1S-DAug couples traditional geometric perturbations with controlled noise injection and a denoising diffusion process conditioned on the original image. The generated images are then encoded and aggregated, alongside the original image, into a combined representation for more robust FSL predictions. Integrated as a training-free model-agnostic plugin, 1S-DAug consistently improves FSL across standard benchmarks of 4 different datasets without any model parameter update, including achieving up to 20\% proportional accuracy improvement on the miniImagenet 5-way-1-shot benchmark. Code will be released.

Chenxing Wei, Hong Wang, Ying He et al.

Large Language Models (LLMs) employ multi-turn interaction as a fundamental paradigm for completing complex tasks. However, their performance often degrades in extended interactions, as they are typically trained on static, single-turn data, which hinders their ability to adapt to real-time user feedback. To address this limitation, we first propose a new paradigm: Test-Time Policy Adaptation for Multi-Turn Interactions (T2PAM), which utilizes user feedback from the ongoing interaction as a reward signal to estimate a latent optimal policy aligned with user preferences, then updates a small subset of parameters to steer the model toward this policy, ultimately enabling efficient in-conversation self-correction. We then introduce Optimum-Referenced One-Step Adaptation (ROSA), a lightweight algorithm that operationalizes T2PAM. ROSA guides the model parameters toward a theoretical optimal policy in a single, efficient update step, avoiding costly iterative gradient-based optimization and minimizing computational overhead. We provide a rigorous theoretical analysis guaranteeing that the policy of ROSA converges to the preference of user as the number of interactions increases. Extensive experiments on challenging benchmark demonstrate that ROSA achieves significant improvements in both task effectiveness and efficiency.

Yao Shu, Shaofeng Cai, Zhongxiang Dai et al.

Recent years have witnessed a surging interest in Neural Architecture Search (NAS). Various algorithms have been proposed to improve the search efficiency and effectiveness of NAS, i.e., to reduce the search cost and improve the generalization performance of the selected architectures, respectively. However, the search efficiency of these algorithms is severely limited by the need for model training during the search process. To overcome this limitation, we propose a novel NAS algorithm called NAS at Initialization (NASI) that exploits the capability of a Neural Tangent Kernel in being able to characterize the converged performance of candidate architectures at initialization, hence allowing model training to be completely avoided to boost the search efficiency. Besides the improved search efficiency, NASI also achieves competitive search effectiveness on various datasets like CIFAR-10/100 and ImageNet. Further, NASI is shown to be label- and data-agnostic under mild conditions, which guarantees the transferability of architectures selected by our NASI over different datasets.

Min Zhang, Yao Shu, Kun He

Finite-sum optimization plays an important role in the area of machine learning, and hence has triggered a surge of interest in recent years. To address this optimization problem, various randomized incremental gradient methods have been proposed with guaranteed upper and lower complexity bounds for their convergence. Nonetheless, these lower bounds rely on certain conditions: deterministic optimization algorithm, or fixed probability distribution for the selection of component functions. Meanwhile, some lower bounds even do not match the upper bounds of the best known methods in certain cases. To break these limitations, we derive tight lower complexity bounds of randomized incremental gradient methods, including SAG, SAGA, SVRG, and SARAH, for two typical cases of finite-sum optimization. Specifically, our results tightly match the upper complexity of Katyusha or VRADA when each component function is strongly convex and smooth, and tightly match the upper complexity of SDCA without duality and of KatyushaX when the finite-sum function is strongly convex and the component functions are average smooth.

Yao Shu, Wei Wang, Shaofeng Cai

Neural architecture search (NAS) searches architectures automatically for given tasks, e.g., image classification and language modeling. Improving the search efficiency and effectiveness have attracted increasing attention in recent years. However, few efforts have been devoted to understanding the generated architectures. In this paper, we first reveal that existing NAS algorithms (e.g., DARTS, ENAS) tend to favor architectures with wide and shallow cell structures. These favorable architectures consistently achieve fast convergence and are consequently selected by NAS algorithms. Our empirical and theoretical study further confirms that their fast convergence derives from their smooth loss landscape and accurate gradient information. Nonetheless, these architectures may not necessarily lead to better generalization performance compared with other candidate architectures in the same search space, and therefore further improvement is possible by revising existing NAS algorithms.

Shaofeng Cai, Yao Shu, Wei Wang et al.

The deployment of deep neural networks in real-world applications is mostly restricted by their high inference costs. Extensive efforts have been made to improve the accuracy with expert-designed or algorithm-searched architectures. However, the incremental improvement is typically achieved with increasingly more expensive models that only a small portion of input instances really need. Inference with a static architecture that processes all input instances via the same transformation would thus incur unnecessary computational costs. Therefore, customizing the model capacity in an instance-aware manner is much needed for higher inference efficiency. In this paper, we propose Dynamic Routing Networks (DRNets), which support efficient instance-aware inference by routing the input instance to only necessary transformation branches selected from a candidate set of branches for each connection between transformation nodes. The branch selection is dynamically determined via the corresponding branch importance weights, which are first generated from lightweight hypernetworks (RouterNets) and then recalibrated with Gumbel-Softmax before the selection. Extensive experiments show that DRNets can reduce a substantial amount of parameter size and FLOPs during inference with prediction performance comparable to state-of-the-art architectures.

Junzhe Zhang, Sai Ho Yeung, Yao Shu et al.

GPU (graphics processing unit) has been used for many data-intensive applications. Among them, deep learning systems are one of the most important consumer systems for GPU nowadays. As deep learning applications impose deeper and larger models in order to achieve higher accuracy, memory management becomes an important research topic for deep learning systems, given that GPU has limited memory size. Many approaches have been proposed towards this issue, e.g., model compression and memory swapping. However, they either degrade the model accuracy or require a lot of manual intervention. In this paper, we propose two orthogonal approaches to reduce the memory cost from the system perspective. Our approaches are transparent to the models, and thus do not affect the model accuracy. They are achieved by exploiting the iterative nature of the training algorithm of deep learning to derive the lifetime and read/write order of all variables. With the lifetime semantics, we are able to implement a memory pool with minimal fragments. However, the optimization problem is NP-complete. We propose a heuristic algorithm that reduces up to 13.3% of memory compared with Nvidia's default memory pool with equal time complexity. With the read/write semantics, the variables that are not in use can be swapped out from GPU to CPU to reduce the memory footprint. We propose multiple swapping strategies to automatically decide which variable to swap and when to swap out (in), which reduces the memory cost by up to 34.2% without communication overhead.

Kun He, Jingbo Wang, Haochuan Li et al.

Toward a deeper understanding on the inner work of deep neural networks, we investigate CNN (convolutional neural network) using DCN (deconvolutional network) and randomization technique, and gain new insights for the intrinsic property of this network architecture. For the random representations of an untrained CNN, we train the corresponding DCN to reconstruct the input images. Compared with the image inversion on pre-trained CNN, our training converges faster and the yielding network exhibits higher quality for image reconstruction. It indicates there is rich information encoded in the random features; the pre-trained CNN may discard information irrelevant for classification and encode relevant features in a way favorable for classification but harder for reconstruction. We further explore the property of the overall random CNN-DCN architecture. Surprisingly, images can be inverted with satisfactory quality. Extensive empirical evidence as well as theoretical analysis are provided.