NeurIPS 2023 论文列表

Spiking neural networks (SNNs) serve as one type of efficient model to process spatio-temporal patterns in time series, such as the Address-Event Representation data collected from Dynamic Vision Sensor (DVS). Although convolutional SNNs have achieved remarkable performance on these AER datasets, benefiting from the predominant spatial feature extraction ability of convolutional structure, they ignore temporal features related to sequential time points. In this paper, we develop a recurrent spiking neural network (RSNN) model embedded with an advanced spiking convolutional block attention module (SCBAM) component to combine both spatial and temporal features of spatio-temporal patterns. It invokes the history information in spatial and temporal channels adaptively through SCBAM, which brings the advantages of efficient memory calling and history redundancy elimination. The performance of our model was evaluated in DVS128-Gesture dataset and other time-series datasets. The experimental results show that the proposed SRNN-SCBAM model makes better use of the history information in spatial and temporal dimensions with less memory space, and achieves higher accuracy compared to other models.

Over the last decade, deep neural networks have transformed our society, and they are already widely applied in various machine learning applications. State-of-the-art deep neural networks are becoming larger in size every year to deliver increasing model accuracy, and as a result, model training consumes substantial computing resources and will only consume more in the future. Using current training methods, in each iteration, to process a data point $x \in \mathbb{R}^d$ in a layer, we need to spend $\Theta(md)$ time to evaluate all the $m$ neurons in the layer. This means processing the entire layer takes $\Theta(nmd)$ time for $n$ data points. Recent work [Song, Yang and Zhang, NeurIPS 2021] reduces this time per iteration to $o(nmd)$, but requires exponential time to preprocess either the data or the neural network weights, making it unlikely to have practical usage. In this work, we present a new preprocessing method that simply stores the weight-data correlation in a tree data structure in order to quickly and dynamically detect which neurons fire at each iteration. Our method requires only $O(nmd)$ time in preprocessing and still achieves $o(nmd)$ time per iteration. We complement our new algorithm with a lower bound, proving that assuming a popular conjecture from complexity theory, one could not substantially speed up our algorithm for dynamic detection of firing neurons.

We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the gradient flow to a global optimum of the non-convex optimization problem in a simple univariate setting. The number of neurons need not be asymptotically large for our result to hold, distinguishing our result from popular recent approaches such as the neural tangent kernel or mean-field regimes. Experimental illustration is provided, showing that the stochastic gradient descent behaves according to our description of the gradient flow and thus converges to a global optimum in the two-timescale regime, but can fail outside of this regime.

Normalizing flow is a class of deep generative models for efficient sampling and likelihood estimation, which achieves attractive performance, particularly in high dimensions. The flow is often implemented using a sequence of invertible residual blocks. Existing works adopt special network architectures and regularization of flow trajectories. In this paper, we develop a neural ODE flow network called JKO-iFlow, inspired by the Jordan-Kinderleherer-Otto (JKO) scheme, which unfolds the discrete-time dynamic of the Wasserstein gradient flow. The proposed method stacks residual blocks one after another, allowing efficient block-wise training of the residual blocks, avoiding sampling SDE trajectories and score matching or variational learning, thus reducing the memory load and difficulty in end-to-end training. We also develop adaptive time reparameterization of the flow network with a progressive refinement of the induced trajectory in probability space to improve the model accuracy further. Experiments with synthetic and real data show that the proposed JKO-iFlow network achieves competitive performance compared with existing flow and diffusion models at a significantly reduced computational and memory cost.

While multi-exit neural networks are regarded as a promising solution for making efficient inference via early exits, combating adversarial attacks remains a challenging problem. In multi-exit networks, due to the high dependency among different submodels, an adversarial example targeting a specific exit not only degrades the performance of the target exit but also reduces the performance of all other exits concurrently. This makes multi-exit networks highly vulnerable to simple adversarial attacks. In this paper, we propose NEO-KD, a knowledge-distillation-based adversarial training strategy that tackles this fundamental challenge based on two key contributions. NEO-KD first resorts to neighbor knowledge distillation to guide the output of the adversarial examples to tend to the ensemble outputs of neighbor exits of clean data. NEO-KD also employs exit-wise orthogonal knowledge distillation for reducing adversarial transferability across different submodels. The result is a significantly improved robustness against adversarial attacks. Experimental results on various datasets/models show that our method achieves the best adversarial accuracy with reduced computation budgets, compared to the baselines relying on existing adversarial training or knowledge distillation techniques for multi-exit networks.

Link prediction attempts to predict whether an unseen edge exists based on only a portion of the graph. A flurry of methods has been created in recent years that attempt to make use of graph neural networks (GNNs) for this task. Furthermore, new and diverse datasets have also been created to better evaluate the effectiveness of these new models. However, multiple limitations currently exist that hinders our ability to properly evaluate these new methods. This includes, but is not limited to: (1) The underreporting of performance on multiple baselines, (2) A lack of a unified data split and evaluation metric on some datasets, (3) An unrealistic evaluation setting that produces negative samples that are easy to classify. To overcome these challenges we first conduct a fair comparison across prominent methods and datasets, utilizing the same dataset settings and hyperparameter settings. We then create a new real-world evaluation setting that samples difficult negative samples via multiple heuristics. The new evaluation setting helps promote new challenges and opportunities in link prediction by aligning the evaluation with real-world situations.

Modeling continuous-time dynamics on irregular time series is critical to account for data evolution and correlations that occur continuously. Traditional methods including recurrent neural networks or Transformer models leverage inductive bias via powerful neural architectures to capture complex patterns. However, due to their discrete characteristic, they have limitations in generalizing to continuous-time data paradigms. Though neural ordinary differential equations (Neural ODEs) and their variants have shown promising results in dealing with irregular time series, they often fail to capture the intricate correlations within these sequences. It is challenging yet demanding to concurrently model the relationship between input data points and capture the dynamic changes of the continuous-time system. To tackle this problem, we propose ContiFormer that extends the relation modeling of vanilla Transformer to the continuous-time domain, which explicitly incorporates the modeling abilities of continuous dynamics of Neural ODEs with the attention mechanism of Transformers. We mathematically characterize the expressive power of ContiFormer and illustrate that, by curated designs of function hypothesis, many Transformer variants specialized in irregular time series modeling can be covered as a special case of ContiFormer. A wide range of experiments on both synthetic and real-world datasets have illustrated the superior modeling capacities and prediction performance of ContiFormer on irregular time series data. The project link is https://seqml.github.io/contiformer/.

Self-supervised learning is introduced to train graph neural networks (GNNs) by employing propagation-based GNNs designed for semi-supervised learning tasks. Unfortunately, this common choice tends to cause two serious issues. Firstly, global parameters cause the model lack the ability to capture the local property. Secondly, it is difficult to handle networks beyond homophily without label information. This paper tends to break through the common choice of employing propagation-based GNNs, which aggregate representations of nodes belonging to different classes and tend to lose discriminative information. If the propagation in each ego-network is just between the nodes from the same class, the obtained representation matrix should follow the low-rank characteristic. To meet this requirement, this paper proposes the Low-Rank Decomposition-based GNNs (LRD-GNN-Matrix) by employing Low-Rank Decomposition to the attribute matrix. Furthermore, to incorporate long-distance information, Low-Rank Tensor Decomposition-based GNN (LRD-GNN-Tensor) is proposed by constructing the node attribute tensor from selected similar ego-networks and performing Low-Rank Tensor Decomposition. The employed tensor nuclear norm facilitates the capture of the long-distance relationship between original and selected similar ego-networks. Extensive experiments demonstrate the superior performance and the robustness of LRD-GNNs.

Graph models based on factorization of the adjacency matrix often fail to capture network structures related to links between dissimilar nodes (heterophily). We introduce a novel graph factorization model that leverages two nonnegative vectors per node to interpretably account for links between both similar and dissimilar nodes. We prove that our model can exactly represent any graph with low *arboricity*, a property that many real-world networks satisfy; our proof also applies to related models but has much greater scope than the closest prior bound, which is based on low *max degree*. Our factorization also has compelling properties besides expressiveness: due to its symmetric structure and nonnegativity, fitting the model inherently finds node communities, and the model's link predictions can be interpreted in terms of these communities. In experiments on real-world networks, we demonstrate our factorization's effectiveness on a variety of tasks, including community detection and link prediction.

Graph condensation, which reduces the size of a large-scale graph by synthesizing a small-scale condensed graph as its substitution, has immediate benefits for various graph learning tasks. However, existing graph condensation methods rely on the joint optimization of nodes and structures in the condensed graph, and overlook critical issues in effectiveness and generalization ability. In this paper, we advocate a new Structure-Free Graph Condensation paradigm, named SFGC, to distill a large-scale graph into a small-scale graph node set without explicit graph structures, i.e., graph-free data. Our idea is to implicitly encode topology structure information into the node attributes in the synthesized graph-free data, whose topology is reduced to an identity matrix. Specifically, SFGC contains two collaborative components: (1) a training trajectory meta-matching scheme for effectively synthesizing small-scale graph-free data; (2) a graph neural feature score metric for dynamically evaluating the quality of the condensed data. Through training trajectory meta-matching, SFGC aligns the long-term GNN learning behaviors between the large-scale graph and the condensed small-scale graph-free data, ensuring comprehensive and compact transfer of informative knowledge to the graph-free data. Afterward, the underlying condensed graph-free data would be dynamically evaluated with the graph neural feature score, which is a closed-form metric for ensuring the excellent expressiveness of the condensed graph-free data. Extensive experiments verify the superiority of SFGC across different condensation ratios.

Graph Contrastive Learning (GCL) has emerged as a popular training approach for learning node embeddings from augmented graphs without labels. Despite the key principle that maximizing the similarity between positive node pairs while minimizing it between negative node pairs is well established, some fundamental problems are still unclear. Considering the complex graph structure, are some nodes consistently well-trained and following this principle even with different graph augmentations? Or are there some nodes more likely to be untrained across graph augmentations and violate the principle? How to distinguish these nodes and further guide the training of GCL? To answer these questions, we first present experimental evidence showing that the training of GCL is indeed imbalanced across all nodes. To address this problem, we propose the metric "node compactness", which is the lower bound of how a node follows the GCL principle related to the range of augmentations. We further derive the form of node compactness theoretically through bound propagation, which can be integrated into binary cross-entropy as a regularization. To this end, we propose the PrOvable Training (POT) for GCL, which regularizes the training of GCL to encode node embeddings that follows the GCL principle better. Through extensive experiments on various benchmarks, POT consistently improves the existing GCL approaches, serving as a friendly plugin.

Complex-valued representation exists inherently in the time-sequential data that can be derived from the integration of harmonic waves. The non-stationary spectral kernel, realizing a complex-valued feature mapping, has shown its potential to analyze the time-varying statistical characteristics of the time-sequential data, as a result of the modeling frequency parameters. However, most existing spectral kernel-based methods eliminate the imaginary part, thereby limiting the representation power of the spectral kernel. To tackle this issue, we propose a generalized spectral kernel network, namely, \underline{Co}mplex-valued \underline{s}pectral kernel \underline{Net}work (CosNet), which includes spectral kernel mapping generalization (SKMG) module and complex-valued spectral kernel embedding (CSKE) module. Concretely, the SKMG module is devised to generalize the spectral kernel mapping in the real number domain to the complex number domain, recovering the inherent complex-valued representation for the real-valued data. Then a following CSKE module is further developed to combine the complex-valued spectral kernels and neural networks to effectively capture long-range or periodic relations of the data. Along with the CosNet, we study the effect of the complex-valued spectral kernel mapping via theoretically analyzing the bound of covering number and generalization error. Extensive experiments demonstrate that CosNet performs better than the mainstream kernel methods and complex-valued neural networks.

Interacting particle systems have proven highly successful in various machine learning tasks, including approximate Bayesian inference and neural network optimization. However, the analysis of these systems often relies on the simplifying assumption of the \emph{mean-field} limit, where particle numbers approach infinity and infinitesimal step sizes are used. In practice, discrete time steps, finite particle numbers, and complex integration schemes are employed, creating a theoretical gap between continuous-time and discrete-time processes. In this paper, we present a novel framework that establishes a precise connection between these discrete-time schemes and their corresponding mean-field limits in terms of convergence properties and asymptotic behavior. By adopting a dynamical system perspective, our framework seamlessly integrates various numerical schemes that are typically analyzed independently. For example, our framework provides a unified treatment of optimizing an infinite-width two-layer neural network and sampling via Stein Variational Gradient descent, which were previously studied in isolation.

Multiplications are responsible for most of the computational cost involved in neural network training and inference. Recent research has thus looked for ways to reduce the cost associated with them. Inspired by Mogami 2020, we replace multiplication with a cheap piecewise affine approximation that is achieved by adding the bit representation of the floating point numbers together as integers. We show that transformers can be trained with the resulting modified matrix multiplications on both vision and language tasks with little to no performance impact, and without changes to the training hyperparameters. We further replace all non-linearities in the networks making them fully and jointly piecewise affine in both inputs and weights. Finally, we show that we can eliminate all multiplications in the entire training process, including operations in the forward pass, backward pass and optimizer update, demonstrating the first successful training of modern neural network architectures in a fully multiplication-free fashion.

Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have attracted increasing concerns. Existing graph condensation methods primarily focus on optimizing the feature matrices of condensed graphs while overlooking the impact of the structure information from the original graphs. To investigate the impact of the structure information, we conduct analysis from the spectral domain and empirically identify substantial Laplacian Energy Distribution (LED) shifts in previous works. Such shifts lead to poor performance in cross-architecture generalization and specific tasks, including anomaly detection and link prediction. In this paper, we propose a novel Structure-broadcasting Graph Dataset Distillation (\textbf{SGDD}) scheme for broadcasting the original structure information to the generation of the synthetic one, which explicitly prevents overlooking the original structure information. Theoretically, the synthetic graphs by SGDD are expected to have smaller LED shifts than previous works, leading to superior performance in both cross-architecture settings and specific tasks. We validate the proposed SGDD~across 9 datasets and achieve state-of-the-art results on all of them: for example, on YelpChi dataset, our approach maintains 98.6\% test accuracy of training on the original graph dataset with 1,000 times saving on the scale of the graph. Moreover, we empirically evaluate there exist 17.6\% $\sim$ 31.4\% reductions in LED shift crossing 9 datasets. Extensive experiments and analysis verify the effectiveness and necessity of the proposed designs. The code will be made public.

The design automation of analog circuits poses significant challenges in terms of the large design space, complex interdependencies between circuit specifications, and resource-intensive simulations. To address these challenges, this paper presents an innovative framework called the Graph of Circuits Explorer (GCX). Leveraging graph structure learning along with graph neural networks, GCX enables the creation of a surrogate model that facilitates efficient exploration of the optimal design space within a semi-supervised learning framework which reduces the need for large labelled datasets. The proposed approach comprises three key stages. First, we learn the geometric representation of circuits and enrich it with technology information to create a comprehensive feature vector. Subsequently, integrating feature-based graph learning with few-shot and zero-shot learning enhances the generalizability in predictions for unseen circuits. Finally, we introduce two algorithms namely, EASCO and ASTROG which upon integration with GCX optimize the available samples to yield the optimal circuit configuration meeting the designer's criteria. The effectiveness of the proposed approach is demonstrated through simulated performance evaluation of various circuits, using derived parameters in 180nm CMOS technology. Furthermore, the generalizability of the approach is extended to higher-order topologies and different technology nodes such as 65nm and 45nm CMOS process nodes.

We study the parameterized complexity of training two-layer neural networks with respect to the dimension of the input data and the number of hidden neurons, considering ReLU and linear threshold activation functions. Albeit the computational complexity of these problems has been studied numerous times in recent years, several questions are still open. We answer questions by Arora et al. (ICLR 2018) and Khalife and Basu (IPCO 2022) showing that both problems are NP-hard for two dimensions, which excludes any polynomial-time algorithm for constant dimension. We also answer a question by Froese et al. (JAIR 2022) proving W[1]-hardness for four ReLUs (or two linear threshold neurons) with zero training error. Finally, in the ReLU case, we show fixed-parameter tractability for the combined parameter number of dimensions and number of ReLUs if the network is assumed to compute a convex map. Our results settle the complexity status regarding these parameters almost completely.

The Strong Lottery Ticket Hypothesis (SLTH) states that randomly-initialised neural networks likely contain subnetworks that perform well without any training. Although unstructured pruning has been extensively studied in this context, its structured counterpart, which can deliver significant computational and memory efficiency gains, has been largely unexplored. One of the main reasons for this gap is the limitations of the underlying mathematical tools used in formal analyses of the SLTH. In this paper, we overcome these limitations: we leverage recent advances in the multidimensional generalisation of the Random Subset-Sum Problem and obtain a variant that admits the stochastic dependencies that arise when addressing structured pruning in the SLTH. We apply this result to prove, for a wide class of random Convolutional Neural Networks, the existence of structured subnetworks that can approximate any sufficiently smaller network. This result provides the first sub-exponential bound around the SLTH for structured pruning, opening up new avenues for further research on the hypothesis and contributing to the understanding of the role of over-parameterization in deep learning.

Message passing neural networks (MPNNs) have emerged as the most popular framework of graph neural networks (GNNs) in recent years. However, their expressive power is limited by the 1-dimensional Weisfeiler-Lehman (1-WL) test. Some works are inspired by $k$-WL/FWL (Folklore WL) and design the corresponding neural versions. Despite the high expressive power, there are serious limitations in this line of research. In particular, (1) $k$-WL/FWL requires at least $O(n^k)$ space complexity, which is impractical for large graphs even when $k=3$; (2) The design space of $k$-WL/FWL is rigid, with the only adjustable hyper-parameter being $k$. To tackle the first limitation, we propose an extension, $(k, t)$-FWL. We theoretically prove that even if we fix the space complexity to $O(n^k)$ (for any $k \geq 2$) in $(k, t)$-FWL, we can construct an expressiveness hierarchy up to solving the graph isomorphism problem. To tackle the second problem, we propose $k$-FWL+, which considers any equivariant set as neighbors instead of all nodes, thereby greatly expanding the design space of $k$-FWL. Combining these two modifications results in a flexible and powerful framework $(k, t)$-FWL+. We demonstrate $(k, t)$-FWL+ can implement most existing models with matching expressiveness. We then introduce an instance of $(k,t)$-FWL+ called Neighborhood$^2$-FWL (N$^2$-FWL), which is practically and theoretically sound. We prove that N$^2$-FWL is no less powerful than 3-WL, and can encode many substructures while only requiring $O(n^2)$ space. Finally, we design its neural version named **N$^2$-GNN** and evaluate its performance on various tasks. N$^2$-GNN achieves record-breaking results on ZINC-Subset (**0.059**), outperforming previous SOTA results by 10.6\%. Moreover, N$^2$-GNN achieves new SOTA results on the BREC dataset (**71.8\%**) among all existing high-expressive GNN methods.