NeurIPS 2024 论文列表

Spiking Transformers, which integrate Spiking Neural Networks (SNNs) with Transformer architectures, have attracted significant attention due to their potential for low energy consumption and high performance. However, there remains a substantial gap in performance between SNNs and Artificial Neural Networks (ANNs). To narrow this gap, we have developed QKFormer, a direct training spiking transformer with the following features: i) _Linear complexity and high energy efficiency_, the novel spike-form Q-K attention module efficiently models the token or channel attention through binary vectors and enables the construction of larger models. ii) _Multi-scale spiking representation_, achieved by a hierarchical structure with the different numbers of tokens across blocks. iii) _Spiking Patch Embedding with Deformed Shortcut (SPEDS)_, enhances spiking information transmission and integration, thus improving overall performance. It is shown that QKFormer achieves significantly superior performance over existing state-of-the-art SNN models on various mainstream datasets. Notably, with comparable size to Spikformer (66.34 M, 74.81\%), QKFormer (64.96 M) achieves a groundbreaking top-1 accuracy of **85.65\%** on ImageNet-1k, substantially outperforming Spikformer by **10.84\%**. To our best knowledge, this is the first time that directly training SNNs have exceeded 85\% accuracy on ImageNet-1K.

The concept of probabilistic values, such as Beta Shapley values and weighted Banzhaf values, has gained recent attention in applications like feature attribution and data valuation. However, exact computation of these values is often exponentially expensive, necessitating approximation techniques. Prior research has shown that the choice of probabilistic values significantly impacts downstream performance, with no universally superior option. Consequently, one may have to approximate multiple candidates and select the best-performing one. Although there have been many efforts to develop efficient estimators, none are intended to approximate all probabilistic values both simultaneously and efficiently. In this work, we embark on the first exploration of achieving this goal. Adhering to the principle of maximum sample reuse and avoiding amplifying factors, we propose a one-sample-fits-all framework parameterized by a sampling vector to approximate intermediate terms that can be converted to any probabilistic value. Leveraging the concept of $ (\epsilon, \delta) $-approximation, we theoretically identify a key formula that effectively determines the convergence rate of our framework. By optimizing the sampling vector using this formula, we obtain i) a one-for-all estimator that achieves the currently best time complexity for all probabilistic values on average, and ii) a faster generic estimator with the sampling vector optimally tuned for each probabilistic value. Particularly, our one-for-all estimator achieves the fastest convergence rate on Beta Shapley values, including the well-known Shapley value, both theoretically and empirically. Finally, we establish a connection between probabilistic values and the least square regression used in (regularized) datamodels, showing that our one-for-all estimator can solve a family of datamodels simultaneously. Our code is available at https://github.com/watml/one-for-all.

In practical distributed systems, workers are typically not homogeneous, and due to differences in hardware configurations and network conditions, can have highly varying processing times. We consider smooth nonconvex finite-sum (empirical risk minimization) problems in this setup and introduce a new parallel method, Freya PAGE, designed to handle arbitrarily heterogeneous and asynchronous computations. By being robust to "stragglers" and adaptively ignoring slow computations, Freya PAGE offers significantly improved time complexity guarantees compared to all previous methods, including Asynchronous SGD, Rennala SGD, SPIDER, and PAGE, while requiring weaker assumptions. The algorithm relies on novel generic stochastic gradient collection strategies with theoretical guarantees that can be of interest on their own, and may be used in the design of future optimization methods. Furthermore, we establish a lower bound for smooth nonconvex finite-sum problems in the asynchronous setup, providing a fundamental time complexity limit. This lower bound is tight and demonstrates the optimality of Freya PAGE in the large-scale regime, i.e., when $\sqrt{m} \geq n,$ where $n$ is \# of workers, and $m$ is \# of data samples.

We study the batched best arm identification (BBAI) problem, where the learner's goal is to identify the best arm while switching the policy as less as possible. In particular, we aim to find the best arm with probability $1-\delta$ for some small constant $\delta>0$ while minimizing both the sample complexity (total number of arm pulls) and the batch complexity (total number of batches). We propose the three-batch best arm identification (Tri-BBAI) algorithm, which is the first batched algorithm that achieves the optimal sample complexity in the asymptotic setting (i.e., $\delta\rightarrow 0$) and runs in $3$ batches in expectation. Based on Tri-BBAI, we further propose the almost optimal batched best arm identification (Opt-BBAI) algorithm, which is the first algorithm that achieves the near-optimal sample and batch complexity in the non-asymptotic setting (i.e., $1/\delta$ is finite), while enjoying the same batch and sample complexity as Tri-BBAI when $\delta$ tends to zero. Moreover, in the non-asymptotic setting, the complexity of previous batch algorithms is usually conditioned on the event that the best arm is returned (with a probability of at least $1-\delta$), which is potentially unbounded in cases where a sub-optimal arm is returned. In contrast, the complexity of Opt-BBAI does not rely on such an event. This is achieved through a novel procedure that we design for checking whether the best arm is eliminated, which is of independent interest.

Beyond the text detection and recognition tasks in image text spotting, video text spotting presents an augmented challenge with the inclusion of tracking. While advanced end-to-end trainable methods have shown commendable performance, the pursuit of multi-task optimization may pose the risk of producing sub-optimal outcomes for individual tasks. In this paper, we identify a main bottleneck in the state-of-the-art video text spotter: the limited recognition capability. In response to this issue, we propose to efficiently turn an off-the-shelf query-based image text spotter into a specialist on video and present a simple baseline termed GoMatching, which focuses the training efforts on tracking while maintaining strong recognition performance. To adapt the image text spotter to video datasets, we add a rescoring head to rescore each detected instance's confidence via efficient tuning, leading to a better tracking candidate pool. Additionally, we design a long-short term matching module, termed LST-Matcher, to enhance the spotter's tracking capability by integrating both long- and short-term matching results via Transformer. Based on the above simple designs, GoMatching delivers new records on ICDAR15-video, DSText, BOVText, and our proposed novel test set with arbitrary-shaped text termed ArTVideo, which demonstates GoMatching's capability to accommodate general, dense, small, arbitrary-shaped, Chinese and English text scenarios while saving considerable training budgets. The code will be released.

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.

Persistent homology is a popular computational tool for analyzing the topology of point clouds, such as the presence of loops or voids. However, many real-world datasets with low intrinsic dimensionality reside in an ambient space of much higher dimensionality. We show that in this case traditional persistent homology becomes very sensitive to noise and fails to detect the correct topology. The same holds true for existing refinements of persistent homology. As a remedy, we find that spectral distances on the k-nearest-neighbor graph of the data, such as diffusion distance and effective resistance, allow to detect the correct topology even in the presence of high-dimensional noise. Moreover, we derive a novel closed-form formula for effective resistance, and describe its relation to diffusion distances. Finally, we apply these methods to high-dimensional single-cell RNA-sequencing data and show that spectral distances allow robust detection of cell cycle loops.

Neural ordinary differential equations (Neural ODEs) is a family of continuous-depth neural networks where the evolution of hidden states is governed by learnable temporal derivatives. We identify a significant limitation in applying traditional Batch Normalization (BN) to Neural ODEs, due to a fundamental mismatch --- BN was initially designed for discrete neural networks with no temporal dimension, whereas Neural ODEs operate continuously over time. To bridge this gap, we introduce temporal adaptive Batch Normalization (TA-BN), a novel technique that acts as the continuous-time analog to traditional BN. Our empirical findings reveal that TA-BN enables the stacking of more layers within Neural ODEs, enhancing their performance. Moreover, when confined to a model architecture consisting of a single Neural ODE followed by a linear layer, TA-BN achieves 91.1\% test accuracy on CIFAR-10 with 2.2 million parameters, making it the first \texttt{unmixed} Neural ODE architecture to approach MobileNetV2-level parameter efficiency. Extensive numerical experiments on image classification and physical system modeling substantiate the superiority of TA-BN compared to baseline methods.

In the 1990s, the constant error carousel and gating were introduced as the central ideas of the Long Short-Term Memory (LSTM). Since then, LSTMs have stood the test of time and contributed to numerous deep learning success stories, in particular they constituted the first Large Language Models (LLMs). However, the advent of the Transformer technology with parallelizable self-attention at its core marked the dawn of a new era, outpacing LSTMs at scale. We now raise a simple question: How far do we get in language modeling when scaling LSTMs to billions of parameters, leveraging the latest techniques from modern LLMs, but mitigating known limitations of LSTMs? Firstly, we introduce exponential gating with appropriate normalization and stabilization techniques. Secondly, we modify the LSTM memory structure, obtaining: (i) sLSTM with a scalar memory, a scalar update, and new memory mixing, (ii) mLSTM that is fully parallelizable with a matrix memory and a covariance update rule. Integrating these LSTM extensions into residual block backbones yields xLSTM blocks that are then residually stacked into xLSTM architectures. Exponential gating and modified memory structures boost xLSTM capabilities to perform favorably when compared to state-of-the-art Transformers and State Space Models, both in performance and scaling.

Foundation models have made significant strides in understanding the genomic language of DNA sequences. However, previous models typically adopt the tokenization methods designed for natural language, which are unsuitable for DNA sequences due to their unique characteristics. In addition, the optimal approach to tokenize DNA remains largely under-explored, and may not be intuitively understood by humans even if discovered. To address these challenges, we introduce MxDNA, a novel framework where the model autonomously learns an effective DNA tokenization strategy through gradient decent. MxDNA employs a sparse Mixture of Convolution Experts coupled with a deformable convolution to model the tokenization process, with the discontinuous, overlapping, and ambiguous nature of meaningful genomic segments explicitly considered. On Nucleotide Transformer Benchmarks and Genomic Benchmarks, MxDNA demonstrates superior performance to existing methods with less pretraining data and time, highlighting its effectiveness. Finally, we show that MxDNA learns unique tokenization strategy distinct to those of previous methods and captures genomic functionalities at a token level during self-supervised pretraining. Our MxDNA aims to provide a new perspective on DNA tokenization, potentially offering broad applications in various domains and yielding profound insights. Code is available at https://github.com/qiaoqiaoLF/MxDNA.

In tabular prediction tasks, tree-based models combined with automated feature engineering methods often outperform deep learning approaches that rely on learned representations. While these feature engineering techniques are effective, they typically depend on a pre-defined search space and primarily use validation scores for feature selection, thereby missing valuable insights from previous experiments. To address these limitations, we propose a novel tabular learning framework that utilizes large language models (LLMs), termed Optimizing Column feature generator with decision Tree reasoning (OCTree). Our key idea is to leverage the reasoning capabilities of LLMs to identify effective feature generation rules without manually specifying the search space and provide language-based reasoning information highlighting past experiments as feedback for iterative rule improvements. We use decision trees to convey this reasoning information, as they can be easily represented in natural language, effectively providing knowledge from prior experiments (i.e., the impact of the generated features on performance) to the LLMs. Our empirical results demonstrate that OCTree consistently enhances the performance of various prediction models across diverse benchmarks, outperforming competing automated feature engineering methods. Code is available at https://github.com/jaehyun513/OCTree.

This paper studies the properties of solutions to multi-task shallow ReLU neural network learning problems, wherein the network is trained to fit a dataset with minimal sum of squared weights. Remarkably, the solutions learned for each individual task resemble those obtained by solving a kernel regression problem, revealing a novel connection between neural networks and kernel methods. It is known that single-task neural network learning problems are equivalent to a minimum norm interpolation problem in a non-Hilbertian Banach space, and that the solutions of such problems are generally non-unique. In contrast, we prove that the solutions to univariate-input, multi-task neural network interpolation problems are almost always unique, and coincide with the solution to a minimum-norm interpolation problem in a Sobolev (Reproducing Kernel) Hilbert Space. We also demonstrate a similar phenomenon in the multivariate-input case; specifically, we show that neural network learning problems with large numbers of tasks are approximately equivalent to an $\ell^2$ (Hilbert space) minimization problem over a fixed kernel determined by the optimal neurons.

We introduce Buffer of Thoughts (BoT), a novel and versatile thought-augmented reasoning approach for enhancing accuracy, efficiency and robustness of large language models (LLMs). Specifically, we propose meta-buffer to store a series of informative high-level thoughts, namely thought-template, distilled from the problem-solving processes across various tasks. Then for each problem, we retrieve a relevant thought-template and adaptively instantiate it with specific reasoning structures to conduct efficient reasoning. To guarantee the scalability and stability, we further propose buffer-manager to dynamically update the meta-buffer, thus enhancing the capacity of meta-buffer as more tasks are solved. We conduct extensive experiments on 10 challenging reasoning-intensive tasks, and achieve significant performance improvements over previous SOTA methods: 11\% on Game of 24, 20\% on Geometric Shapes and 51\% on Checkmate-in-One. Further analysis demonstrate the superior generalization ability and model robustness of our BoT, while requiring only 12\% of the cost of multi-query prompting methods (e.g., tree/graph of thoughts) on average. Code is available at: https://github.com/YangLing0818/buffer-of-thought-llm

Gaze following and social gaze prediction are fundamental tasks providing insights into human communication behaviors, intent, and social interactions. Most previous approaches addressed these tasks separately, either by designing highly specialized social gaze models that do not generalize to other social gaze tasks or by considering social gaze inference as an ad-hoc post-processing of the gaze following task. Furthermore, the vast majority of gaze following approaches have proposed models that can handle only one person at a time and are static, therefore failing to take advantage of social interactions and temporal dynamics. In this paper, we address these limitations and introduce a novel framework to jointly predict the gaze target and social gaze label for all people in the scene. It comprises (i) a temporal, transformer-based architecture that, in addition to frame tokens, handles person-specific tokens capturing the gaze information related to each individual; (ii) a new dataset, VSGaze, built from multiple gaze following and social gaze datasets by extending and validating head detections and tracks, and unifying annotation types. We demonstrate that our model can address and benefit from training on all tasks jointly, achieving state-of-the-art results for multi-person gaze following and social gaze prediction. Our annotations and code will be made publicly available.

Public benchmarks play an essential role in the evaluation of large language models. However, data contamination can lead to inflated performance, rendering them unreliable for model comparison. It is therefore crucial to detect contamination and estimate its impact on measured performance. Unfortunately, existing detection methods can be easily evaded and fail to quantify contamination. To overcome these limitations, we propose a novel definition of *contamination as artificially inflated and non-generalizing benchmark performance* instead of the inclusion of benchmark samples in the training data. This perspective enables us to detect *any* model with inflated performance, i.e., performance that does not generalize to rephrased samples, synthetic samples from the same distribution, or different benchmarks for the same task. Based on this insight, we develop ConStat, a statistical method that reliably detects and quantifies contamination by comparing performance between a primary and reference benchmark relative to a set of reference models. We demonstrate the effectiveness of ConStat in an extensive evaluation of diverse model architectures, benchmarks, and contamination scenarios and find high levels of contamination in multiple popular models including Mistral, Llama, Yi, and the top-3 Open LLM Leaderboard models.

Generative modelling paradigms based on denoising diffusion processes have emerged as a leading candidate for conditional sampling in inverse problems. In many real-world applications, we often have access to large, expensively trained unconditional diffusion models, which we aim to exploit for improving conditional sampling. Most recent approaches are motivated heuristically and lack a unifying framework, obscuring connections between them. Further, they often suffer from issues such as being very sensitive to hyperparameters, being expensive to train or needing access to weights hidden behind a closed API. In this work, we unify conditional training and sampling using the mathematically well-understood Doob's h-transform. This new perspective allows us to unify many existing methods under a common umbrella. Under this framework, we propose DEFT (Doob's h-transform Efficient FineTuning), a new approach for conditional generation that simply fine-tunes a very small network to quickly learn the conditional $h$-transform, while keeping the larger unconditional network unchanged. DEFT is much faster than existing baselines while achieving state-of-the-art performance across a variety of linear and non-linear benchmarks. On image reconstruction tasks, we achieve speedups of up to 1.6$\times$, while having the best perceptual quality on natural images and reconstruction performance on medical images. Further, we also provide initial experiments on protein motif scaffolding and outperform reconstruction guidance methods.

Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learned from a (single) training set, assumed to issue from an unknown probability distribution. In actual deployment, however, the data distribution may (and often does) vary, causing domain adaptation/generalization issues. In this paper we lay the foundations for a `credal' theory of learning, using convex sets of probabilities (credal sets) to model the variability in the data-generating distribution. Such credal sets, we argue, may be inferred from a finite sample of training sets. Bounds are derived for the case of finite hypotheses spaces (both assuming realizability or not), as well as infinite model spaces, which directly generalize classical results.

Text-conditioned motion synthesis has made remarkable progress with the emergence of diffusion models. However, the majority of these motion diffusion models are primarily designed for a single character and overlook multi-human interactions. In our approach, we strive to explore this problem by synthesizing human motion with interactions for a group of characters of any size in a zero-shot manner. The key aspect of our approach is the adaptation of human-wise interactions as pairs of human joints that can be either in contact or separated by a desired distance. In contrast to existing methods that necessitate training motion generation models on multi-human motion datasets with a fixed number of characters, our approach inherently possesses the flexibility to model human interactions involving an arbitrary number of individuals, thereby transcending the limitations imposed by the training data. We introduce a novel controllable motion generation method, InterControl, to encourage the synthesized motions maintaining the desired distance between joint pairs. It consists of a motion controller and an inverse kinematics guidance module that realistically and accurately aligns the joints of synthesized characters to the desired location. Furthermore, we demonstrate that the distance between joint pairs for human-wise interactions can be generated using an off-the-shelf Large Language Model (LLM). Experimental results highlight the capability of our framework to generate interactions with multiple human characters and its potential to work with off-the-shelf physics-based character simulators. Code is available at https://github.com/zhenzhiwang/intercontrol.

The success of machine learning models relies heavily on effectively representing high-dimensional data. However, ensuring data representations capture human-understandable concepts remains difficult, often requiring the incorporation of prior knowledge and decomposition of data into multiple subspaces. Traditional linear methods fall short in modeling more than one space, while more expressive deep learning approaches lack interpretability. Here, we introduce Supervised Independent Subspace Principal Component Analysis ($\texttt{sisPCA}$), a PCA extension designed for multi-subspace learning. Leveraging the Hilbert-Schmidt Independence Criterion (HSIC), $\texttt{sisPCA}$ incorporates supervision and simultaneously ensures subspace disentanglement. We demonstrate $\texttt{sisPCA}$'s connections with autoencoders and regularized linear regression and showcase its ability to identify and separate hidden data structures through extensive applications, including breast cancer diagnosis from image features, learning aging-associated DNA methylation changes, and single-cell analysis of malaria infection. Our results reveal distinct functional pathways associated with malaria colonization, underscoring the essentiality of explainable representation in high-dimensional data analysis.