论文检索

Deep Learning · Generative Models and Autoencoders

Khalid OUBLAL, Said Ladjal, David Benhaiem, Emmanuel LE BORGNE, François Roueff

Learning disentangled representations for time series is a promising path to facilitate reliable generalization to in- and out-of distribution (OOD), offering benefits like feature derivation and improved interpretability and fairness, thereby enhancing downstream tasks. We focus on disentangled representation learning for home appliance electricity usage, enabling users to understand and optimize their consumption for a reduced carbon footprint. Our approach frames the problem as disentangling each attribute's role in total consumption. Unlike existing methods assuming attribute independence which leads to non-identiability, we acknowledge real-world time series attribute correlations, learned up to a smooth bijection using contrastive learning and a single autoencoder. To address this, we propose a Disentanglement under Independence-Of-Support via Contrastive Learning (DIOSC), facilitating representation generalization across diverse correlated scenarios. Our method utilizes innovative \textit{l}-variational inference layers with self-attention, effectively addressing temporal dependencies across bottom-up and top-down networks. We find that DIOSC can enhance the task of representation of time series electricity consumption. We introduce TDS (Time Disentangling Score) to gauge disentanglement quality. TDS reliably reflects disentanglement performance, making it a valuable metric for evaluating time series representations disentanglement. Code available at https://institut-polytechnique-de-paris.github.io/time-disentanglement-lib.

Deep Learning · Generative Models and Autoencoders

Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long, Lingjie Liu, Taku Komura, Wenping Wang

In this paper, we present a novel diffusion model called SyncDreamer that generates multiview-consistent images from a single-view image. Using pretrained large-scale 2D diffusion models, recent work Zero123 demonstrates the ability to generate plausible novel views from a single-view image of an object. However, maintaining consistency in geometry and colors for the generated images remains a challenge. To address this issue, we propose a synchronized multiview diffusion model that models the joint probability distribution of multiview images, enabling the generation of multiview-consistent images in a single reverse process. SyncDreamer synchronizes the intermediate states of all the generated images at every step of the reverse process through a 3D-aware feature attention mechanism that correlates the corresponding features across different views. Experiments show that SyncDreamer generates images with high consistency across different views, thus making it well-suited for various 3D generation tasks such as novel-view-synthesis, text-to-3D, and image-to-3D. Project page: https://liuyuan-pal.github.io/SyncDreamer/.

Deep Learning · Generative Models and Autoencoders

Xin Liu, Muhammad Khalifa, Lu Wang

A model is considered well-calibrated when its probability estimate aligns with the actual likelihood of the output being correct. Calibrating language models (LMs) is crucial, as it plays a vital role in detecting and mitigating hallucinations of LMs as well as building more trustworthy models. However, standard calibration techniques may not be suited for LM calibration. For instance, post-processing methods such as temperature scaling do not reorder the candidate generations. On the other hand, training-based methods require fine-tuning the entire model, which is impractical for LMs of large scale. We present LitCab, a lightweight calibration mechanism consisting of a single linear layer that takes the input text representation and predicts a bias term, which is then added to the LM output logits. LitCab improves model calibration by only adding < 2% of the original model parameters. For evaluation, we construct CaT, a benchmark consisting of eight text generation tasks, covering responses ranging from short phrases to paragraphs. We test LitCab with Llama2-7B, where it improves calibration across all tasks, reducing the average ECE score by as large as 30%. We further conduct a comprehensive evaluation with multiple popular open-sourced LMs from GPT and LLaMA families, yielding the following key findings: (i) Larger models within the same family exhibit better calibration on tasks with short generation tasks, but not necessarily for longer ones. (ii) GPT-family models show superior calibration compared to LLaMA, Llama2, and Vicuna models, despite having much fewer parameters. (iii) Fine-tuning pretrained model (e.g., LLaMA) with samples of limited purpose (e.g., conversations) may lead to worse calibration, highlighting the importance of fine-tuning setups for calibrating LMs.

Deep Learning · Generative Models and Autoencoders

Alexander Ashcroft, Ayan Das, Yulia Gryaditskaya, Zhiyu Qu, Yi-Zhe Song

Vector drawings are innately interactive as they preserve creational cues. Despitethis desirable property they remain relatively under explored due to the difficultiesin modeling complex vector drawings. This is in part due to the primarily _sequential and auto-regressive nature_ of existing approaches failing to scale beyond simpledrawings. In this paper, we define generative models over _highly complex_ vectordrawings by first representing them as “stroke-clouds” – _sets_ of arbitrary cardinality comprised of semantically meaningful strokes. The dimensionality of thestrokes is a design choice that allows the model to adapt to a range of complexities.We learn to encode these _set of strokes_ into compact latent codes by a probabilisticreconstruction procedure backed by _De-Finetti’s Theorem of Exchangability_. Theparametric generative model is then defined over the latent vectors of the encodedstroke-clouds. The resulting “Latent stroke-cloud generator (LSG)” thus capturesthe distribution of complex vector drawings on an implicit _set space_. We demonstrate the efficacy of our model on complex drawings (a newly created Animeline-art dataset) through a rangeof generative tasks.

Deep Learning · Generative Models and Autoencoders

Hyosoon Jang, Minsu Kim, Sungsoo Ahn

This paper studies generative flow networks (GFlowNets) to sample objects from the Boltzmann energy distribution via a sequence of actions. In particular, we focus on improving GFlowNet with partial inference: training flow functions with the evaluation of the intermediate states or transitions. To this end, the recently developed forward-looking GFlowNet reparameterizes the flow functions based on evaluating the energy of intermediate states. However, such an evaluation of intermediate energies may (i) be too expensive or impossible to evaluate and (ii) even provide misleading training signals under large energy fluctuations along the sequence of actions. To resolve this issue, we propose learning energy decompositions for GFlowNets (LED-GFN). Our main idea is to (i) decompose the energy of an object into learnable potential functions defined on state transitions and (ii) reparameterize the flow functions using the potential functions. In particular, to produce informative local credits, we propose to regularize the potential to change smoothly over the sequence of actions. It is also noteworthy that training GFlowNet with our learned potential can preserve the optimal policy. We empirically verify the superiority of LED-GFN in five problems including the generation of unstructured and maximum independent sets, molecular graphs, and RNA sequences.

Deep Learning · Generative Models and Autoencoders

Yunhui Jang, Dongwoo Kim, Sungsoo Ahn

Generating graphs from a target distribution is a significant challenge across many domains, including drug discovery and social network analysis. In this work, we introduce a novel graph generation method leveraging $K^2$ representation, originally designed for lossless graph compression. The $K^2$ representation enables compact generation while concurrently capturing an inherent hierarchical structure of a graph. In addition, we make contributions by (1) presenting a sequential $K^2$ representation that incorporates pruning, flattening, and tokenization processes and (2) introducing a Transformer-based architecture designed to generate the sequence by incorporating a specialized tree positional encoding scheme. Finally, we extensively evaluate our algorithm on four general and two molecular graph datasets to confirm its superiority for graph generation.

Deep Learning · Generative Models and Autoencoders

Hengrui Zhang, Jiani Zhang, Zhengyuan Shen, Balasubramaniam Srinivasan, Xiao Qin, Christos Faloutsos, Huzefa Rangwala, George Karypis

Recent advances in tabular data generation have greatly enhanced synthetic data quality. However, extending diffusion models to tabular data is challenging due to the intricately varied distributions and a blend of data types of tabular data. This paper introduces TabSyn, a methodology that synthesizes tabular data by leveraging a diffusion model within a variational autoencoder (VAE) crafted latent space. The key advantages of the proposed Tabsyn include (1) Generality: the ability to handle a broad spectrum of data types by converting them into a single unified space and explicitly capturing inter-column relations; (2) Quality: optimizing the distribution of latent embeddings to enhance the subsequent training of diffusion models, which helps generate high-quality synthetic data; (3) Speed: much fewer number of reverse steps and faster synthesis speed than existing diffusion-based methods. Extensive experiments on six datasets with five metrics demonstrate that Tabsyn outperforms existing methods. Specifically, it reduces the error rates by 86% and 67% for column-wise distribution and pair-wise column correlation estimations compared with the most competitive baselines. The code has been made available at https://github.com/amazon-science/tabsyn.

Deep Learning · Theory

Hien Dang, Tho-Huu Tran, Tan Nguyen, Nhat Ho

The posterior collapse phenomenon in variational autoencoder (VAE), where the variational posterior distribution closely matches the prior distribution, can hinder the quality of the learned latent variables. As a consequence of posterior collapse, the latent variables extracted by the encoder in VAE preserve less information from the input data and thus fail to produce meaningful representations as input to the reconstruction process in the decoder. While this phenomenon has been an actively addressed topic related to VAE performance, the theory for posterior collapse remains underdeveloped, especially beyond the standard VAE. In this work, we advance the theoretical understanding of posterior collapse to two important and prevalent yet less studied classes of VAE: conditional VAE and hierarchical VAE. Specifically, via a non-trivial theoretical analysis of linear conditional VAE and hierarchical VAE with two levels of latent, we prove that the cause of posterior collapses in these models includes the correlation between the input and output of the conditional VAE and the effect of learnable encoder variance in the hierarchical VAE. We empirically validate our theoretical findings for linear conditional and hierarchical VAE and demonstrate that these results are also predictive for non-linear cases with extensive experiments.

Miscellaneous Aspects of Machine Learning · General Machine Learning Techniques

Khai Nguyen, Nicola Bariletto, Nhat Ho

Monte Carlo (MC) integration has been employed as the standard approximation method for the Sliced Wasserstein (SW) distance, whose analytical expression involves an intractable expectation. However, MC integration is not optimal in terms of absolute approximation error. To provide a better class of empirical SW, we propose quasi-sliced Wasserstein (QSW) approximations that rely on Quasi-Monte Carlo (QMC) methods. For a comprehensive investigation of QMC for SW, we focus on the 3D setting, specifically computing the SW between probability measures in three dimensions. In greater detail, we empirically evaluate various methods to construct QMC point sets on the 3D unit-hypersphere, including the Gaussian-based and equal area mappings, generalized spiral points, and optimizing discrepancy energies. Furthermore, to obtain an unbiased estimator for stochastic optimization, we extend QSW to Randomized Quasi-Sliced Wasserstein (RQSW) by introducing randomness in the discussed point sets. Theoretically, we prove the asymptotic convergence of QSW and the unbiasedness of RQSW. Finally, we conduct experiments on various 3D tasks, such as point-cloud comparison, point-cloud interpolation, image style transfer, and training deep point-cloud autoencoders, to demonstrate the favorable performance of the proposed QSW and RQSW variants.

Deep Learning · Generative Models and Autoencoders

Xianfan Gu, Chuan Wen, Weirui Ye, Jiaming Song, Yang Gao

Imagining the future trajectory is the key for robots to make sound planning and successfully reach their goals. Therefore, text-conditioned video prediction (TVP) is an essential task to facilitate general robot policy learning.To tackle this task and empower robots with the ability to foresee the future, we propose a sample and computation-efficient model, named Seer, by inflating the pretrained text-to-image (T2I) stable diffusion models along the temporal axis. We enhance the U-Net and language conditioning model by incorporating computation-efficient spatial-temporal attention. Furthermore, we introduce a novel Frame Sequential Text Decomposer module that dissects a sentence's global instruction into temporally aligned sub-instructions, ensuring precise integration into each frame of generation. Our framework allows us to effectively leverage the extensive prior knowledge embedded in pretrained T2I models across the frames. With the adaptable-designed architecture, Seer makes it possible to generate high-fidelity, coherent, and instruction-aligned video frames by fine-tuning a few layers on a small amount of data. The experimental results on Something Something V2 (SSv2), Bridgedata and EpicKitchens-100 datasets demonstrate our superior video prediction performance with around 480-GPU hours versus CogVideo with over 12,480-GPU hours: achieving the 31\% FVD improvement compared to the current SOTA model on SSv2 and 83.7\% average preference in the human evaluation. Our project is available at https://seervideodiffusion.github.io/

Deep Learning · Generative Models and Autoencoders

Druv Pai, Sam Buchanan, Ziyang Wu, Yaodong Yu, Yi Ma

Modern learning frameworks often train deep neural networks with massive amounts of unlabeled data to learn representations by solving simple pretext tasks, then use the representations as foundations for downstream tasks. These networks are empirically designed; as such, they are usually not interpretable, their representations are not structured, and their designs are potentially redundant. White-box deep networks, in which each layer explicitly identifies and transforms structures in the data, present a promising alternative. However, existing white-box architectures have only been shown to work at scale in supervised settings with labeled data, such as classification. In this work, we provide the first instantiation of the white-box design paradigm that can be applied to large-scale unsupervised representation learning. We do this by exploiting a fundamental connection between diffusion, compression, and (masked) completion, deriving a deep transformer-like masked autoencoder architecture, called CRATE-MAE, in which the role of each layer is mathematically fully interpretable: they transform the data distribution to and from a structured representation. Extensive empirical evaluations confirm our analytical insights. CRATE-MAE demonstrates highly promising performance on large-scale imagery datasets while using only ~30% of the parameters compared to the standard masked autoencoder with the same model configuration. The representations learned by CRATE-MAE have explicit structure and also contain semantic meaning.

Theory · Deep Learning

Thaddäus Wiedemer, Jack Brady, Alexander Panfilov, Attila Juhos, Matthias Bethge, Wieland Brendel

Learning representations that generalize to novel compositions of known concepts is crucial for bridging the gap between human and machine perception. One prominent effort is learning object-centric representations, which are widely conjectured to enable compositional generalization. Yet, it remains unclear when this conjecture will be true, as a principled theoretical or empirical understanding of compositional generalization is lacking. In this work, we investigate when compositional generalization is guaranteed for object-centric representations through the lens of identifiability theory. We show that autoencoders that satisfy structural assumptions on the decoder and enforce encoder-decoder consistency will learn object-centric representations that provably generalize compositionally. We validate our theoretical result and highlight the practical relevance of our assumptions through experiments on synthetic image data.

Deep Learning · Generative Models and Autoencoders

Sihyun Yu, Weili Nie, De-An Huang, Boyi Li, Jinwoo Shin, anima anandkumar

Video diffusion models have recently made great progress in generation quality, but are still limited by the high memory and computational requirements. This is because current video diffusion models often attempt to process high-dimensional videos directly. To tackle this issue, we propose content-motion latent diffusion model (CMD), a novel efficient extension of pretrained image diffusion models for video generation. Specifically, we propose an autoencoder that succinctly encodes a video as a combination of a content frame (like an image) and a low-dimensional motion latent representation. The former represents the common content, and the latter represents the underlying motion in the video, respectively. We generate the content frame by fine-tuning a pretrained image diffusion model, and we generate the motion latent representation by training a new lightweight diffusion model. A key innovation here is the design of a compact latent space that can directly utilizes a pretrained image diffusion model, which has not been done in previous latent video diffusion models. This leads to considerably better quality generation and reduced computational costs. For instance, CMD can sample a video 7.7$\times$ faster than prior approaches by generating a video of 512$\times$1024 resolution and length 16 in 3.1 seconds. Moreover, CMD achieves an FVD score of 238.3 on WebVid-10M, 18.5% better than the previous state-of-the-art of 292.4.

Applications · Computer Vision

Katja Schwarz, Seung Wook Kim, Jun Gao, Sanja Fidler, Andreas Geiger, Karsten Kreis

Modern learning-based approaches to 3D-aware image synthesis achieve high photorealism and 3D-consistent viewpoint changes for the generated images. Existing approaches represent instances in a shared canonical space. However, for in-the-wild datasets a shared canonical system can be difficult to define or might not even exist. In this work, we instead model instances in view space, alleviating the need for posed images and learned camera distributions. We find that in this setting, existing GAN-based methods are prone to generating flat geometry and struggle with distribution coverage. We hence propose WildFusion, a new approach to 3D-aware image synthesis based on latent diffusion models (LDMs). We first train an autoencoder that infers a compressed latent representation, which additionallycaptures the images’ underlying 3D structure and enables not only reconstruction but also novel view synthesis. To learn a faithful 3D representation, we leverage cues from monocular depth prediction. Then, we train a diffusion model in the 3D-aware latent space, thereby enabling synthesis of high-quality 3D-consistent image samples, outperforming recent state-of-the-art GAN-based methods. Importantly,our 3D-aware LDM is trained without any direct supervision from multiview images or 3D geometry and does not require posed images or learned pose or camera distributions. It directly learns a 3D representation without relying on canonical camera coordinates. This opens up promising research avenues for scalable 3D-aware image synthesis and 3D content creation from in-the-wild image data.

Deep Learning · Generative Models and Autoencoders

Shaofeng Zhang, Jinfa Huang, Qiang Zhou, zhibin wang, Fan Wang, Jiebo Luo, Junchi Yan

Image outpainting aims to generate the content of an input sub-image beyond its original boundaries. It is an important task in content generation yet remains an open problem for generative models. This paper pushes the technical frontier of image outpainting in two directions that have not been resolved in literature: 1) outpainting with arbitrary and continuous multiples (without restriction), and 2) outpainting in a single step (even for large expansion multiples). Moreover, we develop a method that does not depend on a pre-trained backbone network, which is in contrast commonly required by the previous SOTA outpainting methods. The arbitrary multiple outpainting is achieved by utilizing randomly cropped views from the same image during training to capture arbitrary relative positional information. Specifically, by feeding one view and positional embeddings as queries, we can reconstruct another view. At inference, we generate images with arbitrary expansion multiples by inputting an anchor image and its corresponding positional embeddings. The one-step outpainting ability here is particularly noteworthy in contrast to previous methods that need to be performed for $N$ times to obtain a final multiple which is $N$ times of its basic and fixed multiple. We evaluate the proposed approach (called PQDiff as we adopt a diffusion-based generator as our embodiment, under our proposed \textbf{P}ositional \textbf{Q}uery scheme) on public benchmarks, demonstrating its superior performance over state-of-the-art approaches. Specifically, PQDiff achieves state-of-the-art FID scores on the Scenery (\textbf{21.512}), Building Facades (\textbf{25.310}), and WikiArts (\textbf{36.212}) datasets. Furthermore, under the 2.25x, 5x and 11.7x outpainting settings, PQDiff only takes \textbf{40.6\%}, \textbf{20.3\%} and \textbf{10.2\%} of the time of the benchmark state-of-the-art (SOTA) method.

Miscellaneous Aspects of Machine Learning · Representation Learning

Kai Lagemann, Christian Lagemann, Sach Mukherjee

We propose a new model class aimed at predicting dynamical trajectories from high-dimensional empirical data. This is done by combining variational autoencoders and (spatio-)temporal transformers within a framework designed to enforce certain scientifically-motivated invariances. The models allow inference of system behavior at any continuous time and generalization well beyond the data distributions seen during training. Furthermore, the models do not require an explicit neural ODE formulation, making them efficient and highly scalable in practice. We study behavior through simple theoretical analyses and extensive empirical experiments. The latter investigate the ability to predict the trajectories of complicated systems based on finite data and show that the proposed approaches can outperform existing neural-dynamical models. We study also more general inductive bias in the context of transfer to data obtained under entirely novel system interventions. Overall, our results provide a new framework for efficiently learning complicated dynamics in a data-driven manner, with potential applications in a wide range of fields including physics, biology, and engineering.

Deep Learning · Generative Models and Autoencoders

Arman Isajanyan, Artur Shatveryan, David Kocharian, Zhangyang Wang, Humphrey Shi

Social reward as a form of community recognition provides a strong source ofmotivation for users of online platforms to actively engage and contribute withcontent to accumulate peers approval. In the realm of text-conditioned imagesynthesis, the recent surge in progress has ushered in a collaborative era whereusers and AI systems coalesce to refine visual creations. This co-creative pro-cess in the landscape of online social networks empowers users to craft originalvisual artworks seeking for community validation. Nevertheless, assessing thesemodels in the context of collective community preference introduces distinct chal-lenges. Existing evaluation methods predominantly center on limited size userstudies guided by image quality and alignment with prompts. This work pio-neers a paradigm shift, unveiling Social Reward - an innovative reward modelingframework that leverages implicit feedback from social network users engagedin creative editing of generated images. We embark on an extensive journey ofdataset curation and refinement, drawing from Picsart: an online visual creationand editing platform, yielding a first million-user-scale dataset of implicit humanpreferences for user-generated visual art named Picsart Image-Social. Our anal-ysis exposes the shortcomings of current metrics in modeling community creativepreference of text-to-image models’ outputs, compelling us to introduce a novelpredictive model explicitly tailored to address these limitations. Rigorous quan-titative experiments and user study show that our Social Reward model alignsbetter with social popularity than existing metrics. Furthermore, we utilize So-cial Reward to fine-tune text-to-image models, yielding images that are more fa-vored by not only Social Reward, but also other established metrics. These find-ings highlight the relevance and effectiveness of Social Reward in assessing com-munity appreciation for AI-generated artworks, establishing a closer alignmentwith users’ creative goals: creating popular visual art. Codes can be accessed athttps://github.com/Picsart-AI-Research/Social-Reward

Deep Learning · Generative Models and Autoencoders

Xiangming Zhu, Huayu Deng, Haochen Yuan, Yunbo Wang, Xiaokang Yang

We introduce latent intuitive physics, a transfer learning framework for physics simulation that can infer hidden properties of fluids from a single 3D video and simulate the observed fluid in novel scenes. Our key insight is to use latent features drawn from a learnable prior distribution conditioned on the underlying particle states to capture the invisible and complex physical properties. To achieve this, we train a parametrized prior learner given visual observations to approximate the visual posterior of inverse graphics, and both the particle states and the visual posterior are obtained from a learned neural renderer. The converged prior learner is embedded in our probabilistic physics engine, allowing us to perform novel simulations on unseen geometries, boundaries, and dynamics without knowledge of the true physical parameters. We validate our model in three ways: (i) novel scene simulation with the learned visual-world physics, (ii) future prediction of the observed fluid dynamics, and (iii) supervised particle simulation. Our model demonstrates strong performance in all three tasks.

Deep Learning · Self-Supervised Learning

Sarthak Yadav, Sergios Theodoridis, Lars Kai Hansen, Zheng-Hua Tan

In this work, we propose a Multi-Window Masked Autoencoder (MW-MAE) fitted with a novel Multi-Window Multi-Head Attention (MW-MHA) module that facilitates the modelling of local-global interactions in every decoder transformer block through attention heads of several distinct local and global windows. Empirical results on ten downstream audio tasks show that MW-MAEs consistently outperform standard MAEs in overall performance and learn better general-purpose audio representations, along with demonstrating considerably better scaling characteristics. Investigating attention distances and entropies reveals that MW-MAE encoders learn heads with broader local and global attention. Analyzing attention head feature representations through Projection Weighted Canonical Correlation Analysis (PWCCA) shows that attention heads with the same window sizes across the decoder layers of the MW-MAE learn correlated feature representations which enables each block to independently capture local and global information, leading to a decoupled decoder feature hierarchy.

Deep Learning · Generative Models and Autoencoders

YEFEI HE, Jing Liu, Weijia Wu, Hong Zhou, Bohan Zhuang

Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for low-latency real-world applications is constrained by substantial computational costs and latency issues. Quantization is a dominant way to compress and accelerate diffusion models, where post-training quantization (PTQ) and quantization-aware training (QAT) are two main approaches, each bearing its own properties. While PTQ exhibits efficiency in terms of both time and data usage, it may lead to diminished performance in low bit-width settings. On the other hand, QAT can help alleviate performance degradation but comes with substantial demands on computational and data resources. To capitalize on the advantages while avoiding their respective drawbacks, we introduce a data-free, quantization-aware and parameter-efficient fine-tuning framework for low-bit diffusion models, dubbed EfficientDM, to achieve QAT-level performance with PTQ-like efficiency. Specifically, we propose a quantization-aware variant of the low-rank adapter (QALoRA) that can be merged with model weights and jointly quantized to low bit-width. The fine-tuning process distills the denoising capabilities of the full-precision model into its quantized counterpart, eliminating the requirement for training data. To further enhance performance, we introduce scale-aware optimization to address ineffective learning of QALoRA due to variations in weight quantization scales across different layers. We also employ temporal learned step-size quantization to handle notable variations in activation distributions across denoising steps. Extensive experimental results demonstrate that our method significantly outperforms previous PTQ-based diffusion models while maintaining similar time and data efficiency. Specifically, there is only a marginal $0.05$ sFID increase when quantizing both weights and activations of LDM-4 to 4-bit on ImageNet $256\times256$. Compared to QAT-based methods, our EfficientDM also boasts a $16.2\times$ faster quantization speed with comparable generation quality, rendering it a compelling choice for practical applications.