论文检索

Social Aspects · Privacy

Jiaru Qian, Guancheng Wan, Wenke Huang, Guibin Zhang, Yuxin Wu, Bo Du, Mang Ye

Federated Graph Learning (FGL) proposes an effective approach to collaboratively training Graph Neural Networks (GNNs) while maintaining privacy. Nevertheless, communication efficiency becomes a critical bottleneck in environments with limited resources. In this context, one-shot FGL emerges as a promising solution by restricting communication to a single round. However, prevailing FGL methods face two key challenges in the one-shot setting: 1) They heavily rely on gradual personalized optimization over multiple rounds, undermining the capability of the global model to efficiently generalize across diverse graph structures. 2) They are prone to overfitting to local data distributions due to extreme structural bias, leading to catastrophic forgetting. To address these issues, we introduce **GHOST**, an innovative one-shot FGL framework. In GHOST, we establish a proxy model for each client to leverage diverse local knowledge and integrate it to train the global model. During training, we identify and consolidate parameters essential for capturing topological knowledge, thereby mitigating catastrophic forgetting. Extensive experiments on real-world tasks demonstrate the superiority and generalization capability of GHOST. The code is available at https://github.com/JiaruQian/GHOST.

Deep Learning · Algorithms

Lianbo Ma, Jianlun Ma, Yuee Zhou, Guoyang Xie, Qiang He, Zhichao Lu

Mixed Precision Quantization (MPQ) has become an essential technique for optimizing neural network by determining the optimal bitwidth per layer. Existing MPQ methods, however, face a major hurdle: they require a computationally expensive search for quantization strategies on large-scale datasets. To resolve this issue, we introduce a novel approach that first searches for quantization strategies on small datasets and then generalizes them to large-scale datasets. This approach simplifies the process, eliminating the need for large-scale quantization fine-tuning and only necessitating model weight adjustment. Our method is characterized by three key techniques: sharpness-aware minimization for enhanced quantized model generalization, implicit gradient direction alignment to handle gradient conflicts among different optimization objectives, and an adaptive perturbation radius to accelerate optimization. It offers advantages such as no intricate computation of feature maps and high search efficiency. Both theoretical analysis and experimental results validate our approach. Using the CIFAR10 dataset (just 0.5\% the size of ImageNet training data) for MPQ policy search, we achieved equivalent accuracy on ImageNet with a significantly lower computational cost, while improving efficiency by up to 150\% over the baselines.

Optimization

Nikolaj Jensen, Jamie Vicary

In this work, we propose a new architecture-agnostic method for training idempotent neural networks. An idempotent operator satisfies $f(x) = f(f(x))$, meaning it can be applied iteratively with no effect beyond the first application. Some neural networks used in data transformation tasks, such as image generation and augmentation, can represent non-linear idempotent projections. Using methods from perturbation theory we derive the recurrence relation ${\mathbf{K}' \leftarrow 3\mathbf{K}^2 - 2\mathbf{K}^3}$ for iteratively projecting a real-valued matrix $\mathbf{K}$ onto the manifold of idempotent matrices. Our analysis shows that for linear, single-layer MLP networks this projection 1) has idempotent fixed points, and 2) is attracting only around idempotent points. We give an extension to non-linear networks by considering our approach as a substitution of the gradient for the canonical loss function, achieving an architecture-agnostic training scheme. We provide experimental results for MLP- and CNN-based architectures with significant improvement in idempotent error over the canonical gradient-based approach. Finally, we demonstrate practical applications of the method as we train a generative network successfully using only a simple reconstruction loss paired with our method.

General Machine Learning · Representation Learning

Nikita Zozoulenko, Thomas Cass, Lukas Gonon

We introduce Random Feature Representation Boosting (RFRBoost), a novel method for constructing deep residual random feature neural networks (RFNNs) using boosting theory. RFRBoost uses random features at each layer to learn the functional gradient of the network representation, enhancing performance while preserving the convex optimization benefits of RFNNs. In the case of MSE loss, we obtain closed-form solutions to greedy layer-wise boosting with random features. For general loss functions, we show that fitting random feature residual blocks reduces to solving a quadratically constrained least squares problem. Through extensive numerical experiments on tabular datasets for both regression and classification, we show that RFRBoost significantly outperforms RFNNs and end-to-end trained MLP ResNets in the small- to medium-scale regime where RFNNs are typically applied. Moreover, RFRBoost offers substantial computational benefits, and theoretical guarantees stemming from boosting theory.

General Machine Learning · Representation Learning

Haidong Kang

Neural Architecture Search (NAS) has recently outperformed hand-designed networks in various artificial intelligence areas. However, previous works only target a pre-defined task. For a new task in few-shot learning (FSL) scenarios, the architecture is either searched from scratch, which is neither efficient nor flexible, or borrowed architecture from the ones obtained on other tasks, which may lead to sub-optimal. Can we select the best neural architectures without involving any training and eliminate a significant portion of the search cost for new tasks in FSL? In this work, we provide an affirmative answer by proposing a novel information bottleneck (IB) theory driven \textit{Few-shot Neural Architecture Search} (dubbed, IBFS) framework to address this issue. We first derive that the global convergence of Model-agnostic meta-learning (MAML) can be guaranteed by only considering the first-order loss landscape. Moreover, motivated by the observation that IB provides a unified view toward understanding machine learning models, we propose a novel Zero-Cost method tailored for FSL to rank and select architectures based on their \textit{expressivity} obtained by IB mechanisms. Extensive experiments show that IBFS achieves state-of-the-art performance in FSL without training, which demonstrates the effectiveness of our IBFS.

Deep Learning · Graph Neural Networks

Haibo Chen, Xin Wang, Zeyang Zhang, Haoyang Li, Ling Feng, Wenwu Zhu

Graph foundation models (GFMs) aim to share graph knowledge across diverse domains and tasks to boost graph machine learning. However, existing GFMs rely on hand-designed and fixed graph neural network (GNN) architectures, failing to utilize optimal architectures *w.r.t.* specific domains and tasks, inevitably leading to suboptimal performance in diverse graph domains and tasks. In this paper, we explore graph neural architecture search (GNAS) for GFMs for the first time, which suffers from the problem of *architecture inconsistency*, i.e., the optimal architectures for different tasks and domains vary. We tackle this problem by discovering an invariant graph-architecture relationship across domains and tasks, which imposes three challenges: i) how to capture invariant and variant patterns; ii) how to customize architectures to adapt to diverse domains and tasks; iii) how to mitigate the data domination phenomenon during the architecture search process.To address these challenges, we propose **Auto**mated **G**raph **F**oundation **M**odel with Adaptive Architecture Customization (**AutoGFM**), providing a theoretical analysis to demonstrate the limitations of existing GNAS. Specifically, we first propose a disentangled contrastive graph encoder to learn invariant and variant patterns. Then, we design an invariant-guided architecture customization strategy to customize architectures for data from diverse domains and tasks. Finally, we propose a curriculum architecture customization mechanism to mitigate the phenomenon of particular data dominating the search process. Extensive experiments demonstrate that **AutoGFM** outperforms baselines, achieving state-of-the-art performance.

Deep Learning · Theory

Alberto Bernacchia

Second-order optimization methods, which leverage the local curvature of the loss function, have the potential to dramatically accelerate the training of machine learning models. However, these methods are often hindered by the computational burden of constructing and inverting large curvature matrices with $\mathcal{O}(p^2)$ elements, where $p$ is the number of parameters. In this work, we present a theory that predicts the \emph{exact} structure of the global curvature by leveraging the intrinsic symmetries of neural networks, such as invariance under parameter permutations. For Multi-Layer Perceptrons (MLPs), our approach reveals that the global curvature can be expressed in terms of $\mathcal{O}(d^2 + L^2)$ independent factors, where $d$ is the number of input/output dimensions and $L$ is the number of layers, significantly reducing the computational burden compared to the $\mathcal{O}(p^2)$ elements of the full matrix. These factors can be estimated efficiently, enabling precise curvature computations.To evaluate the practical implications of our framework, we apply second-order optimization to synthetic data, achieving markedly faster convergence compared to traditional optimization methods.Our findings pave the way for a better understanding of the loss landscape of neural networks, and for designing more efficient training methodologies in deep learning.Code: \href{https://github.com/mtkresearch/symo_notebooks}{github.com/mtkresearch/symo\_notebooks}

General Machine Learning · Representation Learning

Siyuan Duan, Yuan Sun, Dezhong Peng, Guiduo Duan, Xi Peng, Peng Hu

Multi-view learning methods primarily focus on enhancing decision accuracy but often neglect the uncertainty arising from the intrinsic drawbacks of data, such as noise, conflicts, etc. To address this issue, several trusted multi-view learning approaches based on the Evidential Theory have been proposed to capture uncertainty in multi-view data. However, their performance is highly sensitive to conflicting views, and their uncertainty estimates, which depend on the total evidence and the number of categories, often underestimate uncertainty for conflicting multi-view instances due to the neglect of inherent conflicts between belief masses. To accurately classify conflicting multi-view instances and precisely estimate their intrinsic uncertainty, we present a novel Deep \underline{Fu}zzy \underline{M}ulti-View \underline{L}earning (\textbf{FUML}) method. Specifically, FUML leverages Fuzzy Set Theory to model the outputs of a classification neural network as fuzzy memberships, incorporating both possibility and necessity measures to quantify category credibility. A tailored loss function is then proposed to optimize the category credibility. To further enhance uncertainty estimation, we propose an entropy-based uncertainty estimation method leveraging category credibility. Additionally, we develop a Dual Reliable Multi-view Fusion (DRF) strategy that accounts for both view-specific uncertainty and inter-view conflict to mitigate the influence of conflicting views in multi-view fusion. Extensive experiments demonstrate that our FUML achieves state-of-the-art performance in terms of both accuracy and reliability.

Applications · Neuroscience, Cognitive Science

Zecheng Hao, Qichao Ma, Kang Chen, Yi Zhang, Zhaofei Yu, Tiejun Huang

Spiking Neural Network (SNN), as a brain-inspired and energy-efficient network, is currently facing the pivotal challenge of exploring a suitable and efficient learning framework. The predominant training methodologies, namely Spatial-Temporal Back-propagation (STBP) and ANN-SNN Conversion, are encumbered by substantial training overhead or pronounced inference latency, which impedes the advancement of SNNs in scaling to larger networks and navigating intricate application domains. In this work, we propose a novel parallel conversion learning framework, which establishes a mathematical mapping relationship between each time-step of the parallel spiking neurons and the cumulative spike firing rate. We theoretically validate the lossless and sorting properties of the conversion process, as well as pointing out the optimal shifting distance for each step. Furthermore, by integrating the above framework with the distribution-aware error calibration technique, we can achieve efficient conversion towards more general activation functions or training-free circumstance. Extensive experiments have confirmed the significant performance advantages of our method for various conversion cases under ultra-low time latency. To our best knowledge, this is the first work which jointly utilizes parallel spiking calculation and ANN-SNN Conversion, providing a highly promising approach for SNN supervised training. Code is available at https://github.com/hzc1208/Parallel_Conversion.

Applications · Neuroscience, Cognitive Science

Yu Liang, Yu Yang, Wenjie Wei, Ammar Belatreche, Shuai Wang, Malu Zhang, Yang Yang

Binary Spiking Neural Networks (BSNNs) offer promising efficiency advantages for resource-constrained computing. However, their training algorithms often require substantial memory overhead due to latent weights storage and temporal processing requirements. To address this issue, we propose Binary Spiking Online (BSO) optimization algorithm, a novel online training algorithm that significantly reduces training memory. BSO directly updates weights through flip signals under the online training framework. These signals are triggered when the product of gradient momentum and weights exceeds a threshold, eliminating the need for latent weights during training. To enhance performance, we propose T-BSO, a temporal-aware variant that leverages the inherent temporal dynamics of BSNNs by capturing gradient information across time steps for adaptive threshold adjustment. Theoretical analysis establishes convergence guarantees for both BSO and T-BSO, with formal regret bounds characterizing their convergence rates. Extensive experiments demonstrate that both BSO and T-BSO achieve superior optimization performance compared to existing training methods for BSNNs. The codes are available at \url{https://github.com/hamingsi/BSO}.

Optimization · Stochastic

Haihan Zhang, Weicheng Lin, Yuanshi Liu, Cong Fang

This paper considers a canonical problem in kernel regression: how good are the model performances when it is trained by the popular online first-order algorithms, compared to the offline ones, such as ridge and ridgeless regression? In this paper, we analyze the foundational single-pass Stochastic Gradient Descent (SGD) in kernel regression under source condition where the optimal predictor can even not belong to the RKHS, i.e. the model is misspecified. Specifically, we focus on the inner product kernel over the sphere and characterize the exact orders of the excess risk curves under different scales of sample sizes $n$ concerning the input dimension $d$. Surprisingly, we show that SGD achieves min-max optimal rates up to constants among all the scales, $without$ suffering the saturation, a prevalent phenomenon observed in (ridge) regression, except when the model is highly misspecified and the learning is in a final stage where $n\gg d^\gamma$ with any constant $\gamma >0$. The main reason for SGD to overcome the curse of saturation is the exponentially decaying step size schedule, a common practice in deep neural network training. As a byproduct, we provide the $first$ provable advantage of the scheme over the iterative averaging method in the common setting.

Deep Learning · Theory

Davide Sartor, Alberto Sinigaglia, Gian Antonio Susto

Imposing input-output constraints in multi-layer perceptrons (MLPs) plays a pivotal role in many real world applications. Monotonicity in particular is a common requirement in applications that need transparent and robust machine learning models. Conventional techniques for imposing monotonicity in MLPs by construction involve the use of non-negative weight constraints and bounded activation functions, which poses well known optimization challenges. In this work, we generalize previous theoretical results, showing that MLPs with non-negative weight constraint and activations that saturate on alternating sides are universal approximators for monotonic functions. Additionally, we show an equivalence between saturation side in the activations and sign of the weight constraint. This connection allows us to prove that MLPs with convex monotone activations and non-positive constrained weights also qualify as universal approximators, in contrast to their non-negative constrained counterparts. This results provide theoretical grounding to the empirical effectiveness observed in previous works, while leading to possible architectural simplification. Moreover, to further alleviate the optimization difficulties, we propose an alternative formulation that allows the network to adjust its activations according to the sign of the weights. This eliminates the requirement for weight reparameterization, easing initialization and improving training stability. Experimental evaluation reinforce the validity of the theoretical results, showing that our novel approach compares favorably to traditional monotonic architectures.

Deep Learning · Graph Neural Networks

Yongjian Zhong, Liao Zhu, Hieu Vu, Bijaya Adhikari

Subgraph neural networks have recently gained prominence for various subgraph-level predictive tasks. However, existing methods either \emph{1)} apply simple standard pooling over graph convolutional networks, failing to capture essential subgraph properties, or \emph{2)} rely on rigid subgraph definitions, leading to suboptimal performance. Moreover, these approaches fail to model long-range dependencies both between and within subgraphs—a critical limitation, as many real-world networks contain subgraphs of varying sizes and connectivity patterns. In this paper, we propose a novel implicit subgraph neural network, the first of its kind, designed to capture dependencies across subgraphs. Our approach also integrates label-aware subgraph-level information. We formulate implicit subgraph learning as a bilevel optimization problem and develop a provably convergent algorithm that requires fewer gradient estimations than standard bilevel optimization methods. We evaluate our approach on real-world networks against state-of-the-art baselines, demonstrating its effectiveness and superiority.

Deep Learning · Algorithms

Jialin Zhao, Yingtao Zhang, Xinghang Li, Huaping Liu, Carlo Cannistraci

The growing demands on GPU memory posed by the increasing number of neural network parameters call for training approaches that are more memory-efficient. Previous memory reduction training techniques, such as Low-Rank Adaptation (LoRA) and ReLoRA, face challenges, with LoRA being constrained by its low-rank structure, particularly during intensive tasks like pre-training, and ReLoRA suffering from saddle point issues. In this paper, we propose **S**parse **S**pectral **T**raining **(SST)** to optimize memory usage for **pre-training**. SST **updates all singular values** and **selectively updates singular vectors** through a multinomial sampling method weighted by the magnitude of the singular values. Furthermore, SST employs **singular value decomposition to initialize and periodically reinitialize** low-rank parameters, reducing distortion relative to full-rank training compared to other low-rank methods. Through comprehensive testing on both Euclidean and hyperbolic neural networks across various tasks, SST demonstrates its ability to outperform existing memory reduction training methods and is comparable to full-rank training in various cases. On LLaMA-1.3B, with only 18.7\% of the parameters trainable compared to full-rank training (using a rank equivalent to 6\% of the embedding dimension), SST reduces the perplexity gap between other low-rank methods and full-rank training by **97.4\%**. This result highlights SST as an effective parameter-efficient technique for model pre-training.

Applications · Chemistry, Physics, and Earth Sciences

Erpai Luo, Xinran Wei, Lin Huang, Yunyang Li, Han Yang, Zaishuo Xia, Zun Wang, Chang Liu, Bin Shao, Jia Zhang

Hamiltonian matrix prediction is pivotal in computational chemistry, serving as the foundation for determining a wide range of molecular properties. While SE(3) equivariant graph neural networks have achieved remarkable success in this domain, their substantial computational cost—driven by high-order tensor product (TP) operations—restricts their scalability to large molecular systems with extensive basis sets. To address this challenge, we introduce **SPH**Net, an efficient and scalable equivariant network, that incorporates adaptive **SP**arsity into **H**amiltonian prediction. SPHNet employs two innovative sparse gates to selectively constrain non-critical interaction combinations, significantly reducing tensor product computations while maintaining accuracy. To optimize the sparse representation, we develop a Three-phase Sparsity Scheduler, ensuring stable convergence and achieving high performance at sparsity rates of up to 70\%. Extensive evaluations on QH9 and PubchemQH datasets demonstrate that SPHNet achieves state-of-the-art accuracy while providing up to a 7x speedup over existing models. Beyond Hamiltonian prediction, the proposed sparsification techniques also hold significant potential for improving the efficiency and scalability of other SE(3) equivariant networks, further broadening their applicability and impact.

Applications · Computer Vision

Lufei Liu, Tor Aamodt

Graphics rendering applications increasingly leverage neural networks in tasks such as denoising, supersampling, and frame extrapolation to improve image quality while maintaining frame rates.The temporal coherence inherent in these tasks presents an opportunity to reuse intermediate results from previous frames and avoid redundant computations.Recent work has shown that caching intermediate features to be reused in subsequent inferences is an effective method to reduce latency in diffusion models.We extend this idea to real-time rendering and present ReFrame, which explores different caching policies to optimize trade-offs between quality and performance in rendering workloads.ReFrame can be applied to a variety of encoder-decoder style networks commonly found in rendering pipelines.Experimental results show that we achieve 1.4$\times$ speedup on average with negligible quality loss in three real-time rendering tasks.Code available: https://ubc-aamodt-group.github.io/reframe-layer-caching/

General Machine Learning

Sudeepta Mondal, Zhuolin Jiang, Ganesh Sundaramoorthi

We present a theory for the construction of out-of-distribution (OOD) detection features for neural networks. We introduce random features for OOD through a novel information-theoretic loss functional consisting of two terms, the first based on the KL divergence separates resulting in-distribution (ID) and OOD feature distributions and the second term is the Information Bottleneck, which favors compressed features that retain the OOD information. We formulate a variational procedure to optimize the loss and obtain OOD features. Based on assumptions on OOD distributions, one can recover properties of existing OOD features, i.e., shaping functions. Furthermore, we show that our theory can predict a new shaping function that out-performs existing ones on OOD benchmarks. Our theory provides a general framework for constructing a variety of new features with clear explainability.

Deep Learning · Algorithms

Emanuel Ben Baruch, Adam Botach, Igor Kviatkovsky, Manoj Aggarwal, Gerard Medioni

With the increasing size of datasets used for training neural networks, data pruning has gained traction in recent years. However, most current data pruning algorithms are limited in their ability to preserve accuracy compared to models trained on the full data, especially in high pruning regimes. In this paper we explore the application of data pruning while incorporating knowledge distillation (KD) when training on a pruned subset. That is, rather than relying solely on ground-truth labels, we also use the soft predictions from a teacher network pre-trained on the complete data. By integrating KD into training, we demonstrate significant improvement across datasets, pruning methods, and on all pruning fractions. We first establish a theoretical motivation for employing self-distillation to improve training on pruned data. Then, we empirically make a compelling and highly practical observation: using KD, simple random pruning is comparable or superior to sophisticated pruning methods across all pruning regimes. On ImageNet for example, we achieve superior accuracy despite training on a random subset of only 50% of the data. Additionally, we demonstrate a crucial connection between the pruning factor and the optimal knowledge distillation weight. This helps mitigate the impact of samples with noisy labels and low-quality images retained by typical pruning algorithms. Finally, we make an intriguing observation: when using lower pruning fractions, larger teachers lead to accuracy degradation, while surprisingly, employing teachers with a smaller capacity than the student's may improve results. Our code will be made available.

Applications · Chemistry, Physics, and Earth Sciences

Qi Wang, Yuan Mi, Wang Haoyun, Yi Zhang, Ruizhi Chengze, Hongsheng Liu, Ji-Rong Wen, Hao Sun

Solving partial differential equations (PDEs) by numerical methods meet computational cost challenge for getting the accurate solution since fine grids and small time steps are required. Machine learning can accelerate this process, but struggle with weak generalizability, interpretability, and data dependency, as well as suffer in long-term prediction. To this end, we propose a PDE-embedded network with multiscale time stepping (MultiPDENet), which fuses the scheme of numerical methods and machine learning, for accelerated simulation of flows. In particular, we design a convolutional filter based on the structure of finite difference stencils with a small number of parameters to optimize, which estimates the equivalent form of spatial derivative on a coarse grid to minimize the equation's residual. A Physics Block with a 4th-order Runge-Kutta integrator at the fine time scale is established that embeds the structure of PDEs to guide the prediction. To alleviate the curse of temporal error accumulation in long-term prediction, we introduce a multiscale time integration approach, where a neural network is used to correct the prediction error at a coarse time scale. Experiments across various PDE systems, including the Navier-Stokes equations, demonstrate that MultiPDENet can accurately predict long-term spatiotemporal dynamics, even given small and incomplete training data, e.g., spatiotemporally down-sampled datasets. MultiPDENet achieves the state-of-the-art performance compared with other neural baseline models, also with clear speedup compared to classical numerical methods

Deep Learning · Graph Neural Networks

Zitong Shi, Guancheng Wan, Wenke Huang, Guibin Zhang, He Li, Carl Yang, Mang Ye

Federated Graph Learning (FGL) has gained significant attention as a privacy-preserving approach to collaborative learning, but the computational demands increase substantially as datasets grow and Graph Neural Network (GNN) layers deepen. To address these challenges, we propose $\textbf{EAGLES}$, a unified sparsification framework. EAGLES applies client-consensus parameter sparsification to generate multiple unbiased subnetworks at varying sparsity levels, reducing the need for iterative adjustments and mitigating performance degradation. In the graph structure domain, we introduced a dual-expert approach: a $\textit{graph sparsification expert}$ uses multi-criteria node-level sparsification, and a $\textit{graph synergy expert}$ integrates contextual node information to produce optimal sparse subgraphs. Furthermore, the framework introduces a novel distance metric that leverages node contextual information to measure structural similarity among clients, fostering effective knowledge sharing. We also introduce the $\textbf{Harmony Sparsification Principle}$, EAGLES balances model performance with lightweight graph and model structures. Extensive experiments demonstrate its superiority, achieving competitive performance on various datasets, such as reducing training FLOPS by 82\% $\downarrow$ and communication costs by 80\% $\downarrow$ on the ogbn-proteins dataset, while maintaining high performance.