In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models. The method reaches state-of-the-art performances in terms of FID and CLIP-Score for few steps image generation on the COCO2014 and COCO2017 datasets, while requiring only several GPU hours of training and fewer trainable parameters than existing methods. In addition to its efficiency, the versatility of the method is also exposed across several tasks such as *text-to-image*, *inpainting*, *face-swapping*, *super-resolution* and using different backbones such as UNet-based denoisers (SD1.5, SDXL), DiT (Pixart) and MMDiT (SD3), as well as adapters. In all cases, the method allowed to reduce drastically the number of sampling steps while maintaining very high-quality image generation.
论文检索
输入标题、作者或关键词，从 9,256 篇学术成果中精准定位
DPCL-Diff：Temporal Knowledge Graph Reasoning Based on Graph Node Diffusion Model with Dual-Domain Periodic Contrastive Learning
PDF ↗Temporal knowledge graph (TKG) reasoning that infers future missing facts is an essential and challenging task. Predicting future events typically relies on closely related historical facts, yielding more accurate results for repetitive or periodic events. However, for future events with sparse historical interactions, the effectiveness of this method, which focuses on leveraging high-frequency historical information, diminishes. Recently, the capabilities of diffusion models in image generation have opened new opportunities for TKG reasoning. Therefore, we propose a graph node diffusion model with dual-domain periodic contrastive learning (DPCL-Diff). Graph node diffusion model (GNDiff) introduces noise into sparsely related events to simulate new events, generating high-quality data that better conforms to the actual distribution. This generative mechanism significantly enhances the model's ability to reason about new events. Additionally, the dual-domain periodic contrastive learning (DPCL) maps periodic and non-periodic event entities to Poincaré and Euclidean spaces, leveraging their characteristics to distinguish similar periodic events effectively. Experimental results on four public datasets demonstrate that DPCL-Diff significantly outperforms state-of-the-art TKG models in event prediction, demonstrating our approach's effectiveness. This study also investigates the combined effectiveness of GNDiff and DPCL in TKG tasks.
FlowPolicy: Enabling Fast and Robust 3D Flow-Based Policy via Consistency Flow Matching for Robot Manipulation
PDF ↗Robots can acquire complex manipulation skills by learning policies from expert demonstrations, which is often known as vision-based imitation learning. Generating policies based on diffusion and flow matching models has been shown to be effective, particularly in robotic manipulation tasks. However, recursion-based approaches are inference inefficient in working from noise distributions to policy distributions, posing a challenging trade-off between efficiency and quality. This motivates us to propose FlowPolicy, a novel framework for fast policy generation based on consistency flow matching and 3D vision. Our approach refines the flow dynamics by normalizing the self-consistency of the velocity field, enabling the model to derive task execution policies in a single inference step. Specifically, FlowPolicy conditions on the observed 3D point cloud, where consistency flow matching directly defines straight-line flows from different time states to the same action space, while simultaneously constraining their velocity values, that is, we approximate the trajectories from noise to robot actions by normalizing the self-consistency of the velocity field within the action space, thus improving the inference efficiency. We validate the effectiveness of FlowPolicy in Adroit and Metaworld, demonstrating a 7× increase in inference speed while maintaining competitive average success rates compared to state-of-the-art methods.
Electroencephalogram (EEG) signals have attracted significant attention from researchers due to their non-invasive nature and high temporal sensitivity in decoding visual stimuli. However, most recent studies have focused solely on the relationship between EEG and image data pairs, neglecting the valuable "beyond-image-modality" information embedded in EEG signals. This results in the loss of critical multimodal information in EEG. To address the limitation, this paper proposes a unified framework that fully leverages multimodal data to represent EEG signals, named CognitionCapturer. Specifically, CognitionCapturer trains modality expert encoders for each modality to extract cross-modal information from the EEG modality. Then, it introduces a diffusion prior to map the EEG embedding space to the CLIP embedding space, followed by using a pretrained generative model, the proposed framework can reconstruct visual stimuli with high semantic and structural fidelity. Notably, the framework does not require any fine-tuning of the generative models and can be extended to incorporate more modalities. Through extensive experiments, we demonstrate that CognitionCapturer outperforms state-of-the-art methods both qualitatively and quantitatively.
With rapid advances in generative artificial intelligence, the text-to-music synthesis task has emerged as a promising direction for music generation. Nevertheless, achieving precise control over multi-track generation remains an open challenge. While existing models excel in directly generating multi-track mix, their limitations become evident when it comes to composing individual tracks and integrating them in a controllable manner. This departure from the typical workflows of professional composers hinders the ability to refine details in specific tracks. To address this gap, we propose JEN-1 Composer, a unified framework designed to efficiently model marginal, conditional, and joint distributions over multi-track music using a single model. Building upon an audio latent diffusion model, JEN-1 Composer extends the versatility of multi-track music generation. We introduce a progressive curriculum training strategy, which gradually escalates the difficulty of training tasks while ensuring the model's generalization ability and facilitating smooth transitions between different scenarios. During inference, users can iteratively generate and select music tracks, thus incrementally composing entire musical pieces in accordance with the Human-AI co-composition workflow. Our approach demonstrates state-of-the-art performance in controllable and high-fidelity multi-track music synthesis, marking a significant advancement in interactive AI-assisted music creation.
Manhattan Self-Attention Diffusion Residual Networks with Dynamic Bias Rectification for BCI-based Few-Shot Learning
PDF ↗The distribution biases and scarcity of samples in multi-source data present significant challenges for few-shot learning (FSL) tasks based on brain-computer interface (BCI). Recent efforts have explored the application of diffusion mechanisms in FSL, typically utilizing labeled data to augment the support set. However, this approach has not effectively utilized unlabeled data nor addressed distribution biases. Inspired by the latest advancements in FSL, we propose the manhattan self-attention diffusion residual networks (MSADiff-Resnet) with dynamic bias rectification. This model explicitly adds the manhattan self-attention diffusion layer to resnet, using attention mechanisms and manhattan distance-based decay function to control local diffusion intensity, and adjusts the global diffusion strength through the parameter. This diffusion mechanism bridges labeled and unlabeled data, addressing the limitations associated with sample availability. Additionally, we effectively tackle the distribution biases of multi-source data through inter-class bias rectification and dynamic intra-class bias rectification. Moreover, this study presents for the first time a universal deep learning framework specifically designed for BCI-based FSL tasks. Extensive experiments on multi-source BCI task datasets have validated the effectiveness of proposed method.
Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with human intents in various tasks. To achieve this, previous methods conduct return-conditioned policy generation or Reinforcement Learning (RL)-based policy optimization, while they both rely on pre-defined reward functions. In this work, we propose a novel framework, Forward KL regularized Preference optimization for aligning Diffusion policies, to align the diffusion policy with preferences directly. We first train a diffusion policy from the offline dataset without considering the preference, and then align the policy to the preference data via direct preference optimization. During the alignment phase, we formulate direct preference learning in a diffusion policy, where the forward KL regularization is employed in preference optimization to avoid generating out-of-distribution actions. We conduct extensive experiments for MetaWorld manipulation and D4RL tasks. The results show our method exhibits superior alignment with preferences and outperforms previous state-of-the-art algorithms.
Procedural Content Generation via Machine Learning (PCGML) has enhanced game content creation, yet challenges in controllability and limited training data persist. This study addresses these issues by distilling a constructive PCG algorithm into a controllable PCGML model. We first generate a large amount of content with a constructive algorithm and label it using a Large Language Model (LLM). We use these synthetic labels to condition two PCGML models for content-specific generation, a diffusion model and the five-dollar model. This neural network distillation process ensures that the generation aligns with the original algorithm while introducing controllability through plain text. We define this text-conditioned PCGML as a Text-to-game-Map (T2M) task, offering an alternative to prevalent text-to-image multi-modal tasks. We compare our distilled models with the baseline constructive algorithm. Our analysis of the variety, accuracy, and quality of our generation demonstrates the efficacy of distilling constructive methods into controllable text-conditioned PCGML models.
Information diffusion prediction (IDP) is a pivotal task for understanding the dynamics of information propagation within social networks. Conventional models typically adhere to a fixed learning-based paradigm, where the trained prediction model remains static during the inference phase. This paradigm presupposes that the data is independent and identically distributed, an assumption that may not hold true due to the inherently open nature of social media and the uncertainty and variability in user behavior. In this paper, we address the novel problem of out-of-distribution (OOD) shifts within IDP tasks and propose a new test-time training-based model for multi-scale IDP tasks, named Ghidorah. Our approach focuses on adapting a subset of model parameters to accommodate the unique characteristics of test samples through self-supervised learning (SSL) tasks. Ghidorah comprises three components: the macroscopic prediction branch, the microscopic prediction branch, and the auxiliary SSL branch. The auxiliary SSL task employs a masked autoencoder-based loss to fine-tune the model for specific test samples prior to prediction. Furthermore, Ghidorah integrates invariant learning to capture robust representations while mitigating spurious correlations. To our knowledge, Ghidorah is the first work to introduce a test-time training framework specifically designed to address the critical yet often overlooked OOD challenges in IDP. Experimental results across several benchmark datasets validate the superiority of our approach.
Addressing Cold-Start Problem in Click-Through Rate Prediction via Supervised Diffusion Modeling
PDF ↗Predicting Click-Through Rates is a crucial function within recommendation and advertising platforms, as the output of CTR prediction determines the order of items shown to users. The Embedding and MLP paradigm has become a standard approach for industrial recommendation systems and has been widely deployed. However, this paradigm suffers from cold-start problems, where there is either no or only limited user action data available, leading to poorly learned ID embeddings. The cold-start problem hampers the performance of new items. To address this problem, we design a novel diffusion model to generate a warmed-up embedding for new items. Specifically, we define a novel diffusion process between the ID embedding space and the side information space. In addition, we can derive a sub-sequence from the diffusion steps to expedite training, given that our diffusion model is non-Markovian. Our diffusion model is supervised by both the variational inference and binary cross-entropy objectives, enabling it to generate warmed-up embeddings for items in both the cold-start and warm-up phases. Additionally, we have conducted extensive experiments on three recommendation datasets. The results confirmed the effectiveness of our approach.
Diffusion-based Semantic Outlier Generation via Nuisance Awareness for Out-of-Distribution Detection
PDF ↗Out-of-distribution (OOD) detection, determining whether a given sample is part of the in-distribution (ID) or not, has been newly explored by a generative model-based outlier synthesizing approach, especially with diffusion models. Nonetheless, existing diffusion models often produce outliers that are considerably distant from the ID in pixel-space, showing limited efficacy for capturing subtle distinctions between ID and OOD. To address these issues, we propose a novel framework, Semantic Outlier generation via Nuisance Awareness (SONA), which directly utilizes informative pixel-space ID images in diffusion models. Thereby, the generated outliers achieve two crucial properties: (i) they closely resemble the ID mainly in nuisances, while (ii) represent discriminative semantic information. To facilitate the separate effect on semantics and nuisances, we introduce SONA guidance, providing region-specific guidance. Extensive experiments demonstrate the effectiveness of our framework, achieving an impressive AUROC of 87% on near-OOD datasets, which surpasses the performance of baseline methods by a significant margin of approximately 6%.
Multimodal recommendation (MMRec) aims to integrate multimodal information of items to address the inherent data sparsity issue in collaborative-based recommendation. Traditional MMRec methods typically capture the structure-level item representations from the observed user behaviors within the multimodal graph, overlooking the potential impact of negative instances for personalized preference understanding. In light of the outstanding generative ability and step-by-step inference characteristic of Diffusion Models (DMs), we propose a Curriculum Conditioned Diffusion framework for Multimodal Recommendation (CCDRec), which precisely excavates the modality-aware distribution-level correlation among multi-modalities and elegantly integrates the reverse phase of DMs into negative sampling to highlight the most suitable instances in a curricular manner. Specifically, CCDRec proposes the Diffusion-controlled Multimodal Aligning module (DMA) to align multimodal knowledge with collaborative signals by capturing the fine-grained relationships among multi-modalities in the probabilistic distribution space. Furthermore, CCDRec designs the Negative-sensitive Diffusive Inferring module (NDI) to progressively synthesize the negative sample pool with diverse hardness to support the following knowledge-aware negative sampling. To gradually ramp up the training complexity, CCDRec further introduces a Curricular Negative Sampler (CNS) to tally the curriculum learning paradigm with the reverse phase of DMA, thereby adaptively sampling the gold-standard negative instances to enhance optimization. Extensive experiments on three datasets with four diverse backbones demonstrate the effectiveness and robustness of our CCDRec. The visualization analyses also clarify the underlying mechanism of our DMA in multimodal representation alignment and CNS in curricular negative discovery. The code and the corresponding dataset will be uploaded in the Appendix.
Recommender systems are increasingly prevalent to provide personalized suggestions and enhance user satisfaction. Typical recommendation models encode users and items as embeddings, and generate recommendations by assessing the similarity between these embeddings. Despite their effectiveness, these embedding-based models struggle with modeling user uncertainty and capturing diverse user interests using a single fixed user embedding. Recent studies have begun to explore a user-distribution paradigm to learn distributions for users. However, this approach employs a single distribution per user, which fails to effectively delineate semantic boundaries, resulting in sub-optimal recommendations. To this end, we propose GCDR, a Guided Conditional Diffusion Recommender model, to learn multiple distributions for each user in this paper. Specifically, GCDR addresses two major challenges: 1) learning disentangled distributions, and 2) learning personalized distributions. GCDR captures inter-user and intra-user distribution properties through conditional and guided diffusion, respectively. It maintains user-specific embeddings to encode long-term interests for conditional diffusion, while for guided diffusion, it incorporates short-term interests encoded from recent interactions with category preferences. To align the diffusion model with the recommendation task, we train GCDR with three loss functions, included the user loss, the recommendation loss and the diffusion loss. Extensive experiments on four real-world datasets show that GCDR is able to learn effective user distributions and is superior to thirteen state-of-the-art baseline methods.
GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation
PDF ↗Retrosynthesis prediction focuses on identifying reactants capable of synthesizing a target product. Typically, the retrosynthesis prediction involves two phases: Reaction Center Identification and Reactant Generation. However, we argue that most existing methods suffer from two limitations in the two phases: (i) Existing models do not adequately capture the ``face'' information in molecular graphs for the reaction center identification. (ii) Current approaches for the reactant generation predominantly use sequence generation in a 2D space, which lacks versatility in generating reasonable distributions for completed reactive groups and overlooks molecules' inherent 3D properties. To overcome the above limitations, we propose GDiffRetro. For the reaction center identification, GDiffRetro uniquely integrates the original graph with its corresponding dual graph to represent molecular structures, which helps guide the model to focus more on the faces in the graph. For the reactant generation, GDiffRetro employs a conditional diffusion model in 3D to further transform the obtained synthon into a complete reactant. Our experimental findings reveal that GDiffRetro outperforms state-of-the-art semi-template models across various evaluative metrics.
Enhancing Diffusion Model with Auxiliary Information Mining-Exploration and Efficient Sampling Mechanism for Sequential Recommendation
PDF ↗Sequential recommendation aims to capture the temporal dependencies of items in a user's historical interactions and make recommendations based on this. Previous generative methods addressed the issue of data not directly reflecting user preference uncertainty by modeling the distribution of latent item representations. Diffusion model (DM)-based methods have achieved significant success due to their high-quality generation and stable training. However, they lack satisfactory user sequence representations to guide the generation process, impacting recommendation performance. Moreover, these methods overlook the drawback of slow inference speed, severely limiting their practical value. To obtain effective generative guidance signals and accelerate the recommendation process, we propose DAE4Rec. In this approach, a Graph Auto-Encoder (GAE) is used to obtain interpretable item node representations, revealing global transitions of items that previous methods struggled to uncover. Then, we use it to construct a generative guidance signal with lower coupling and variance for the diffusion model. Additionally, by employing a non-Markov chain derived from the forward diffusion process, it is the first to implement a 'skip-step' reverse process in diffusion model-based methods. And a creatively designed compensator is used to bridge the performance gap caused by 'skip-step'. Extensive experiments on three real-world datasets demonstrate that DAE4Rec outperforms other state-of-the-art generative sequential recommenders.
Existing sequential recommendation models are mostly based on sequential models, which can be misled by inconsistent items in the local sequence. This study proposes GlobalDiff, a plug-and-play framework to enhance the performance of sequential models by utilizing a diffusion model to restore the global non-sequential data structure of the item universe and compensate for the local sequential context. Several novel techniques are proposed, including training construction, guided reverse approximator, and inference ensemble, to seamlessly integrate the diffusion model with the sequential model. Extensive experiments on various datasets demonstrate that GlobalDiff can enhance advanced sequential models by an average improvement of 9.67%.
Spatiotemporal data imputation plays a crucial role in various fields such as traffic flow monitoring, air quality assessment, and climate prediction. However, spatiotemporal data collected by sensors often suffer from temporal incompleteness, and the sparse and uneven distribution of sensors leads to missing data in the spatial dimension. Among existing methods, autoregressive approaches are prone to error accumulation, while simple conditional diffusion models fail to adequately capture the spatiotemporal relationships between observed and missing data. To address these issues, we propose a novel two-stage Refined Diffusion Probability Impuation (RDPI) framework based on an initial network and a conditional diffusion model. In the initial stage, deterministic imputation methods are used to generate preliminary estimates of the missing data. In the refinement stage, residuals are treated as the diffusion target, and observed values are innovatively incorporated into the forward process. This results in a conditional diffusion model better suited for spatiotemporal data imputation, bridging the gap between the preliminary estimates and the true values. Experiments on multiple datasets demonstrate that RDPI not only achieves state-of-the-art imputation performance but also significantly reduces sampling computational costs.
Public Opinion Field Effect and Hawkes Process Join Hands for Information Popularity Prediction
PDF ↗Information popularity prediction, aiming to predict the growth of user participation in a trending topic diffusion, is a fundamental task in social networks. Existing methods often treat information diffusion as a single independent process, ignoring the ``public opinion field effect'' where multiple trending topics coexist and compete for user attention simultaneously. Inspired by Hawkes theory, we propose a novel Hawkes-process-based learning model for information popularity prediction, which takes into account both the temporal correlation among users' propagation behaviors in several topics diffusion and public opinion field effect in social networks. We first propose an improved neural Hawkes process to capture comprehensive propagation law from multiple dimensions and then propose a novel public opinion field paradigm based on the improved Hawkes process and cascade structure. We design a novel learning framework incorporating the public opinion field paradigm to extract high-quality representations for information popularity prediction. Extensive experiments on four real-world datasets validate that our model significantly outperforms the state-of-the-art competitors.
Bundle recommendation aims to improve user experience by suggesting complementary items that users are likely to purchase together. Although recent advances in recommendation systems have shown promise, there are still significant challenges: i) The dynamic nature of user preferences and interactions introduces noise that can distort the effectiveness of recommendations. ii) Existing methods frequently exhibit limited robustness when addressing the sparsity of user interactions with bundles in real-world scenarios. To tackle these issues, we introduce a disentangled contrastive bundle recommendation (DCBR) framework with conditional diffusion. First, we propose a conditional bundle diffusion model for denoising the user-bundle interaction graph, introducing a bundle latent consistency constraint during the optimization process to mitigate the degradation of original interaction information. Subsequently, we design a triple-view denoised graph learning module to obtain effective representations from multiple views. Furthermore, we present a dual-level disentangled contrastive learning paradigm, which addresses the latent relationships at two levels: between views (inter-view) and within each view (intra-view). By maximizing the consistency between positive samples in these contrastive views, we generate disentangled contrastive signals, overcoming interaction sparsity and alleviating noise issues. Our experimental evaluations on three benchmark datasets reveal that DCBR significantly outperforms state-of-the-art methods.
CasFT: Future Trend Modeling for Information Popularity Prediction with Dynamic Cues-Driven Diffusion Models
PDF ↗The rapid spread of diverse information on online social platforms has prompted both academia and industry to realize the importance of predicting content popularity, which could benefit a wide range of applications, such as recommendation systems and strategic decision-making. Recent works mainly focused on extracting spatiotemporal patterns inherent in the information diffusion process within a given observation period so as to predict its popularity over a future period of time. However, these works often overlook the future popularity trend, as future popularity could either increase exponentially or stagnate, introducing uncertainties to the prediction performance. Additionally, how to transfer the preceding-term dynamics learned from the observed diffusion process into future-term trends remains an unexplored challenge. Against this background, we propose CasFT, which leverages observed information Cascades and dynamic cues extracted via neural ODEs as conditions to guide the generation of Future popularity-increasing Trends through a diffusion model. These generated trends are then combined with the spatiotemporal patterns in the observed information cascade to make the final popularity prediction. Extensive experiments conducted on three real-world datasets demonstrate that CasFT significantly improves the prediction accuracy compared to state-of-the-art approaches.