ICML 2024 Papers

Recent advances in natural language processing have relied heavily on using Transformer-based language models. However, Transformers often require large parameter sizes and model depth. Existing Transformer-free approaches using state-space models demonstrate superiority over Transformers, yet they still lack a neuro-biologically connection to the human brain. This paper proposes ${\it LasF}$, representing ${\bf L}$anguage tokens ${\bf as}$ ${\bf F}$unctionals of semantic fields, to simulate the neuronal behaviors for better language modeling. The ${\it LasF}$ module is equivalent to a nonlinear approximator tailored for sequential data. By replacing the final layers of pre-trained language models with the ${\it LasF}$ module, we obtain ${\it LasF}$-based models. Experiments conducted for standard reading comprehension and question-answering tasks demonstrate that the ${\it LasF}$-based models consistently improve accuracy with fewer parameters. Besides, we use CommonsenseQA's blind test set to evaluate a full-parameter tuned ${\it LasF}$-based model, which outperforms the prior best ensemble and single models by $0.4\%$ and $3.1\%$, respectively. Furthermore, our ${\it LasF}$-only language model trained from scratch outperforms existing parameter-efficient language models on standard datasets such as WikiText103 and PennTreebank.

Despite their groundbreaking performance for many generative modeling tasks, diffusion models have fallen short on discrete data domains such as natural language. Crucially, standard diffusion models rely on the well-established theory of score matching, but efforts to generalize this to discrete structures have not yielded the same empirical gains. In this work, we bridge this gap by proposing score entropy, a novel loss that naturally extends score matching to discrete spaces, integrates seamlessly to build discrete diffusion models, and significantly boosts performance. Experimentally, we test our Score Entropy Discrete Diffusion models (SEDD) on standard language modeling tasks. For comparable model sizes, SEDD beats existing language diffusion paradigms (reducing perplexity by $25$-$75$%) and is competitive with autoregressive models, in particular outperforming GPT-2. Furthermore, compared to autoregressive mdoels, SEDD generates faithful text without requiring distribution annealing techniques like temperature scaling (around $6$-$8\times$ better generative perplexity than un-annealed GPT-2), can trade compute and quality (similar quality with $32\times$ fewer network evaluations), and enables controllable infilling (matching nucleus sampling quality while enabling other strategies besides left to right prompting).

Autoregressive language models are the currently dominant paradigm for text generation, however they have some fundamental limitations that cannot be remedied by scale---for example inherently sequential and unidirectional generation. While alternate classes of models have been explored, we have limited mathematical understanding of their fundamental power and limitations. In this paper we focus on Generative Masked Language Models (GMLMs), a non-autoregressive paradigm in which we train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model. These models empirically strike a promising speed-quality trade-off as each step can be typically parallelized by decoding the entire sequence in parallel. We develop a mathematical framework for analyzing and improving such models which sheds light on questions of sample complexity and inference speed and quality. Empirically, we adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality compared with autoregressive models. We run careful ablation experiments to give recommendations on key design choices, and make fine-grained observations on the common error modes in connection with our theory. Our mathematical analyses and empirical observations characterize both potentials and limitations of this approach, and can be applied to future works on improving understanding and performance of GMLMs. We released codes for our experiments.

Similar to natural language models, pre-trained genome language models are proposed to capture the underlying intricacies within genomes with unsupervised sequence modeling. They have become essential tools for researchers and practitioners in biology. However, the hand-crafted tokenization policies used in these models may not encode the most discriminative patterns from the limited vocabulary of genomic data. In this paper, we introduce VQDNA, a general-purpose framework that renovates genome tokenization from the perspective of genome vocabulary learning. By leveraging vector-quantized codebook as learnable vocabulary, VQDNA can adaptively tokenize genomes into pattern-aware embeddings in an end-to-end manner. To further push its limits, we propose Hierarchical Residual Quantization (HRQ), where varying scales of codebooks are designed in a hierarchy to enrich the genome vocabulary in a coarse-to-fine manner. Extensive experiments on 32 genome datasets demonstrate VQDNA's superiority and favorable parameter efficiency compared to existing genome language models. Notably, empirical analysis of SARS-CoV-2 mutations reveals the fine-grained pattern awareness and biological significance of learned HRQ vocabulary, highlighting its untapped potential for broader applications in genomics.

Probabilistic time series modeling based on generative models has attracted lots of attention because of its wide applications and excellent performance. However, existing state-of-the-art models, based on stochastic differential equation, not only struggle to determine the drift and diffusion coefficients during the design process but also have slow generation speed. To tackle this challenge, we firstly propose decomposable denoising diffusion model ($\text{D}^3\text{M}$) and prove it is a general framework unifying denoising diffusion models and continuous flow models. Based on the new framework, we propose some simple but efficient probability paths with high generation speed. Furthermore, we design a module that combines a special state space model with linear gated attention modules for sequence modeling. It preserves inductive bias and simultaneously models both local and global dependencies. Experimental results on 8 real-world datasets show that $\text{D}^3\text{M}$ reduces RMSE and CRPS by up to 4.6% and 4.3% compared with state-of-the-arts on imputation tasks, and achieves comparable results with state-of-the-arts on forecasting tasks with only 10 steps.

Recent studies have shown that high disparities in effective learning rates (ELRs) across layers in deep neural networks can negatively affect trainability. We formalize how these disparities evolve over time by modeling weight dynamics (evolution of expected gradient and weight norms) of networks with normalization layers, predicting the evolution of layer-wise ELR ratios. We prove that when training with any constant learning rate, ELR ratios converge to 1, despite initial gradient explosion. We identify a "critical learning rate" beyond which ELR disparities widen, which only depends on current ELRs. To validate our findings, we devise a hyper-parameter-free warm-up method that successfully minimizes ELR spread quickly in theory and practice. Our experiments link ELR spread with trainability, a relationship that is most evident in very deep networks with significant gradient magnitude excursions.

Developing an effective molecular generation framework even with a limited number of molecules is often important for its practical deployment, e.g., drug discovery, since acquiring task-related molecular data requires expensive and time-consuming experimental costs. To tackle this issue, we introduce Hierarchical Textual Inversion for Molecular Generation (HI-Mol), a novel data-efficient molecular generation method. HI-Mol is inspired by the importance of hierarchical information, e.g., both coarse- and fine-grained features, in understanding the molecule distribution. We propose to use multi-level embeddings to reflect such hierarchical features based on the adoption of the recent textual inversion technique in the visual domain, which achieves data-efficient image generation. Compared to the conventional textual inversion method in the image domain using a single-level token embedding, our multi-level token embeddings allow the model to effectively learn the underlying low-shot molecule distribution. We then generate molecules based on the interpolation of the multi-level token embeddings. Extensive experiments demonstrate the superiority of HI-Mol with notable data-efficiency. For instance, on QM9, HI-Mol outperforms the prior state-of-the-art method with 50x less training data. We also show the effectiveness of molecules generated by HI-Mol in low-shot molecular property prediction. Code is available at https://github.com/Seojin-Kim/HI-Mol.

Predicting multivariate time series is crucial, demanding precise modeling of intricate patterns, including inter-series dependencies and intra-series variations. Distinctive trend characteristics in each time series pose challenges, and existing methods, relying on basic moving average kernels, may struggle with the non-linear structure and complex trends in real-world data. Given that, we introduce a learnable decomposition strategy to capture dynamic trend information more reasonably. Additionally, we propose a dual attention module tailored to capture inter-series dependencies and intra-series variations simultaneously for better time series forecasting, which is implemented by channel-wise self-attention and autoregressive self-attention. To evaluate the effectiveness of our method, we conducted experiments across eight open-source datasets and compared it with the state-of-the-art methods. Through the comparison results, our $\textbf{Leddam}$ ($\textbf{LE}arnable$ $\textbf{D}ecomposition$ and $\textbf{D}ual $ $\textbf{A}ttention$ $\textbf{M}odule$) not only demonstrates significant advancements in predictive performance but also the proposed decomposition strategy can be plugged into other methods with a large performance-boosting, from 11.87% to 48.56% MSE error degradation. Code is available at this link: https://github.com/Levi-Ackman/Leddam.

Learning the distribution of data on Riemannian manifolds is crucial for modeling data from non-Euclidean space, which is required by many applications in diverse scientific fields. Yet, existing generative models on manifolds suffer from expensive divergence computation or rely on approximations of heat kernel. These limitations restrict their applicability to simple geometries and hinder scalability to high dimensions. In this work, we introduce the Riemannian Diffusion Mixture, a principled framework for building a generative diffusion process on manifolds. Instead of following the denoising approach of previous diffusion models, we construct a diffusion process using a mixture of bridge processes derived on general manifolds without requiring heat kernel estimations. We develop a geometric understanding of the mixture process, deriving the drift as a weighted mean of tangent directions to the data points that guides the process toward the data distribution. We further propose a scalable training objective for learning the mixture process that readily applies to general manifolds. Our method achieves superior performance on diverse manifolds with dramatically reduced number of in-training simulation steps for general manifolds.

The difficulty of partial multi-view multi-label learning lies in coupling the consensus of multi-view data with the task relevance of multi-label classification, under the condition where partial views and labels are unavailable. In this paper, we seek to compress cross-view representation to maximize the proportion of shared information to better predict semantic tags. To achieve this, we establish a model consistent with the information bottleneck theory for learning cross-view shared representation, minimizing non-shared information while maintaining feature validity to help increase the purity of task-relevant information. Furthermore, we model multi-label prototype instances in the latent space and learn label correlations in a data-driven manner. Our method outperforms existing state-of-the-art methods on multiple public datasets while exhibiting good compatibility with both partial and complete data. Finally, we experimentally reveal the importance of condensing shared information under the premise of information balancing, in the process of multi-view information encoding and compression.

This paper introduces SparseTSF, a novel, extremely lightweight model for Long-term Time Series Forecasting (LTSF), designed to address the challenges of modeling complex temporal dependencies over extended horizons with minimal computational resources. At the heart of SparseTSF lies the Cross-Period Sparse Forecasting technique, which simplifies the forecasting task by decoupling the periodicity and trend in time series data. This technique involves downsampling the original sequences to focus on cross-period trend prediction, effectively extracting periodic features while minimizing the model's complexity and parameter count. Based on this technique, the SparseTSF model uses fewer than *1k* parameters to achieve competitive or superior performance compared to state-of-the-art models. Furthermore, SparseTSF showcases remarkable generalization capabilities, making it well-suited for scenarios with limited computational resources, small samples, or low-quality data. The code is publicly available at this repository: https://github.com/lss-1138/SparseTSF.

Implicit neural representations have emerged as a powerful paradigm to represent signals such as images and sounds. This approach aims to utilize neural networks to parameterize the implicit function of the signal. However, when representing implicit functions, traditional neural networks such as ReLU-based multilayer perceptrons face challenges in accurately modeling high-frequency components of signals. Recent research has begun to explore the use of Fourier Neural Networks (FNNs) to overcome this limitation. In this paper, we propose Quantum Implicit Representation Network (QIREN), a novel quantum generalization of FNNs. Furthermore, through theoretical analysis, we demonstrate that QIREN possesses a quantum advantage over classical FNNs. Lastly, we conducted experiments in signal representation, image superresolution, and image generation tasks to show the superior performance of QIREN compared to state-of-the-art (SOTA) models. Our work not only incorporates quantum advantages into implicit neural representations but also uncovers a promising application direction for Quantum Neural Networks.

We develop a novel probabilistic model for interpersonal coordination as a latent phenomenon explaining statistical temporal influence between multiple components in a system. For example, the state of one person can influence that of another at a later time, as indicated by their observed behaviors. We characterize coordination as the degree to which the distributions for such states at one time point are merged for the next salient time point. We evaluate our model in the context of three-person teams executing a virtual search and rescue (SAR) mission. We first use synthetic data to confirm that our technical definition of coordination is consistent with expectations and that we can recover generated coordination despite noise. We then show that captured coordination can be predictive of team performance on real data. Here we use speech vocalics and semantics to infer coordination for 36 teams carrying out two successive SAR missions. In two different datasets, we find that coordination is generally predictive of team score for the second mission, but not for the first, where teams are largely learning to play the game. In addition, we found that including a semantic modality improves prediction in some scenarios. This shows that our intuitive technical definition can capture useful explanatory aspects of team behavior.

Towards energy-efficient artificial intelligence similar to the human brain, the bio-inspired spiking neural networks (SNNs) have advantages of biological plausibility, event-driven sparsity, and binary activation. Recently, large-scale language models exhibit promising generalization capability, making it a valuable issue to explore more general spike-driven models. However, the binary spikes in existing SNNs fail to encode adequate semantic information, placing technological challenges for generalization. This work proposes the first fully spiking mechanism for general language tasks, including both discriminative and generative ones. Different from previous spikes with 0,1 levels, we propose a more general spike formulation with bi-directional, elastic amplitude, and elastic frequency encoding, while still maintaining the addition nature of SNNs. In a single time step, the spike is enhanced by direction and amplitude information; in spike frequency, a strategy to control spike firing rate is well designed. We plug this elastic bi-spiking mechanism in language modeling, named SpikeLM. It is the first time to handle general language tasks with fully spike-driven models, which achieve much higher accuracy than previously possible. SpikeLM also greatly bridges the performance gap between SNNs and ANNs in language modeling. Our code is available at https://github.com/Xingrun-Xing/SpikeLM.

This paper explores the problem of generative modeling, aiming to simulate diverse examples from an unknown distribution based on observed examples. While recent studies have focused on quantifying the statistical precision of popular algorithms, there is a lack of mathematical evaluation regarding the non-replication of observed examples and the creativity of the generative model. We present theoretical insights into this aspect, demonstrating that the Wasserstein GAN, constrained to left-invertible push-forward maps, generates distributions that not only avoid replication but also significantly deviate from the empirical distribution. Importantly, we show that left-invertibility achieves this without compromising the statistical optimality of the resulting generator. Our most important contribution provides a finite-sample lower bound on the Wasserstein-1 distance between the generative distribution and the empirical one. We also establish a finite-sample upper bound on the distance between the generative distribution and the true data-generating one. Both bounds are explicit and show the impact of key parameters such as sample size, dimensions of the ambient and latent spaces, noise level, and smoothness measured by the Lipschitz constant.

Subsurface imaging involves solving full waveform inversion (FWI) to predict geophysical properties from measurements. This problem can be reframed as an image-to-image translation, with the usual approach being to train an encoder-decoder network using paired data from two domains: geophysical property and measurement. A recent seminal work (InvLINT) demonstrates there is only a linear mapping between the latent spaces of the two domains, and the decoder requires paired data for training. This paper extends this direction by demonstrating that only linear mapping necessitates paired data, while both the encoder and decoder can be learned from their respective domains through self-supervised learning. This unveils an intriguing phenomenon (named Auto-Linear) where the self-learned features of two separate domains are automatically linearly correlated. Compared with existing methods, our Auto-Linear has four advantages: (a) solving both forward and inverse modeling simultaneously, (b) reducing model size, (c) enhanced performance, especially when the paired data is limited, and (d) strong generalization ability of the trained encoder and decoder.

Recently, a noticeable trend has emerged in developing pre-trained foundation models in the domains of CV and NLP. However, for molecular pre-training, there lacks a universal model capable of effectively applying to various categories of molecular tasks, since existing prevalent pre-training methods exhibit effectiveness for specific types of downstream tasks. Furthermore, the lack of profound understanding of existing pre-training methods, including 2D graph masking, 2D-3D contrastive learning, and 3D denoising, hampers the advancement of molecular foundation models. In this work, we provide a unified comprehension of existing pre-training methods through the lens of contrastive learning. Thus their distinctions lie in clustering different views of molecules, which is shown beneficial to specific downstream tasks. To achieve a complete and general-purpose molecular representation, we propose a novel pre-training framework, named UniCorn, that inherits the merits of the three methods, depicting molecular views in three different levels. SOTA performance across quantum, physicochemical, and biological tasks, along with comprehensive ablation study, validate the universality and effectiveness of UniCorn.

Protein language models have demonstrated significant potential in the field of protein engineering. However, current protein language models primarily operate at the residue scale, which limits their ability to provide information at the atom level. This limitation prevents us from fully exploiting the capabilities of protein language models for applications involving both proteins and small molecules. In this paper, we propose ESM-AA (ESM All-Atom), a novel approach that enables atom-scale and residue-scale unified molecular modeling. ESM-AA achieves this by pre-training on multi-scale code-switch protein sequences and utilizing a multi-scale position encoding to capture relationships among residues and atoms. Experimental results indicate that ESM-AA surpasses previous methods in protein-molecule tasks, demonstrating the full utilization of protein language models. Further investigations reveal that through unified molecular modeling, ESM-AA not only gains molecular knowledge but also retains its understanding of proteins.

This paper proposes an equivariant neural network that takes data in any finite-dimensional semi-simple Lie algebra as input. The corresponding group acts on the Lie algebra as adjoint operations, making our proposed network adjoint-equivariant. Our framework generalizes the Vector Neurons, a simple $\mathrm{SO}(3)$-equivariant network, from 3-D Euclidean space to Lie algebra spaces, building upon the invariance property of the Killing form. Furthermore, we propose novel Lie bracket layers and geometric channel mixing layers that extend the modeling capacity. Experiments are conducted for the $\mathfrak{so}(3)$, $\mathfrak{sl}(3)$, and $\mathfrak{sp}(4)$ Lie algebras on various tasks, including fitting equivariant and invariant functions, learning system dynamics, point cloud registration, and homography-based shape classification. Our proposed equivariant network shows wide applicability and competitive performance in various domains.