Multi-view representation learning methods typically follow a consistent-and-specific pipeline that aims at extracting latent representations for an entity from its multiple observable views to facilitate downstream tasks. However, most of them overlook the complex underlying correlation between different views. To solve this issue, we delve into a well-known property of neural networks (NNs) that NNs tend to learn simple patterns first and then hard ones. In our case, view-consistent representations are simple patterns and view-specific representations are hard. To this end, we propose to disentangle view-consistency and view-specificity and learn them gradually. Specifically, we devise a novel curriculum learning approach that adjusts the whole model to learn view-consistent representations first and then progressively view-specific representations. Besides, we saddle each view with a learnable prior that allows each view-specific representation to appropriate its distribution. Moreover, we incorporate a mixture-of-experts layer and a disentangling module to further enhance the quality of the learned representations. Extensive experiments on five real-world datasets show that the proposed model outperforms its counterparts markedly. The code is available at https://github.com/XLearning-SCU/2025-IJCAI-CL2P.
论文检索
输入标题、作者或关键词，从 960 篇学术成果中精准定位
Time series imputation is one of the most challenging problems and has broad applications in various fields like health care and the Internet of Things. Existing methods mainly aim to model the temporally latent dependencies and the generation process from the observed time series data. In real-world scenarios, different types of missing mechanisms, like MAR (Missing At Random) and MNAR (Missing Not At Random), can occur in time series data. However, existing methods often overlook the difference among the aforementioned missing mechanisms and use a single model for time series imputation, which can easily lead to misleading results due to mechanism mismatching. In this paper, we propose a framework for the time series imputation problem by exploring Different Missing Mechanisms (DMM in short) and tailoring solutions accordingly. Specifically, we first analyze the data generation processes with temporal latent states and missing cause variables for different mechanisms. Sequentially, we model these generation processes via variational inference and estimate prior distributions of latent variables via a normalizing flow-based neural architecture. Furthermore, we establish identifiability results under the nonlinear independent component analysis framework to show that latent variables are identifiable. Experimental results show that our method surpasses existing time series imputation techniques across various datasets with different missing mechanisms, demonstrating its effectiveness in real-world applications.
Recommender systems play a critical role in many applications by providing personalized recommendations based on user interactions. However, it remains a major challenge to capture complex sequential patterns and address noise in user interaction data. While advanced neural networks have enhanced sequential recommendation by modeling high-order item dependencies, they typically assume that the noisy interaction data as the user's preferred preferences. This assumption can lead to suboptimal recommendation results. We propose a Variational Graph Auto-Encoder driven Graph Enhancement (VGAE-GE) method for robust augmentation in sequential recommendation. Specifically, our method first constructs an item transition graph to capture higher-order interactions and employs a Variational Graph Auto-Encoder (VGAE) to generate latent variable distributions. By utilizing these latent variable distributions for graph reconstruction, we can improve the item representation. Next, we use a Graph Convolutional Network (GCN) to transform these latent variables into embeddings and infer more robust user representations from the updated item embeddings. Finally, we obtain the reconstructed user check-in data, and then use a Mamba-based recommender to make the recommendation process more efficient and the recommendation results more accurate. Extensive experiments on five public datasets demonstrate that our VGAE-GE model improves recommendation performance and robustness.
Counterfactual explanations in Explainable AI (XAI) identify which features to change to alter an outcome, but existing methods adjust only the features of a single agent. We present a new approach to re-evaluating rankings that is based on predictions of future features of the other agents in a ranking system. It uses an algorithm that provides a more realistic counterfactual explanation of changing the ranking of a particular agent. Computer experiments demonstrated that the proposed algorithm can capture the time variation of the entire ranking system in the inference results.
The performance of multimodal models often deteriorates when modality absence occurs. The absence disrupts the learned inter-modal correlations, resulting in biased multimodal representations. This challenge is especially pronounced when the absence is pervasive, affecting both the training and inference phases. Recent studies have attempted to reconstruct the missing information; however, most of them require complete supervision, which is seldom available in scenarios of pervasive absence. The quality of reconstruction remains a critical issue. Alternatively, others aim to learn robust representations from the available modalities but the substantial variations and biases are not fully addressed. This paper introduces the Multimodal Generalization and Refinement (MGR) framework to mitigate the issue of pervasive modality absence. MGR begins by acquiring generalized multimodal representations and iteratively refines them to recognize and calibrate the biased representations. Initially, multimodal samples with absence are embedded through foundation models, and MGR integrates independent unimodal features to further enhance generalization. Additionally, a novel mixed-context prompt is adopted to identify biases in both features and correlations. A redistribution operation can then refine these biases through graph pooling, culminating in robust and calibrated multimodal representations, which are suitable for downstream tasks. Comprehensive experiments on four benchmark datasets demonstrate that the proposed MGR framework outperforms state-of-the-art methods, effectively mitigating the impact of pervasive modality absence.
Few-shot Named Entity Recognition (NER) spotlights the tag of novel entity types in data-limited scenarios or lower-resource settings. Advances with Pre-trained Language Models (PLMs), including BERT, GPT, and their variants, have driven tremendous strategies to leverage context-dependent representations and exploit predefined relational cues, yielding significant gains in witnessing unseen entities. Nevertheless, a fundamental issue exists in prior efforts regarding their susceptibility to adversarial attacks in the intricate semantic environment. This vulnerability undermines the robustness of semantic representations, exacerbating the challenge of accurate entity identification, especially when transitioning across domains. To this end, we propose an Adversity-aware Augment Learning (AAL) solution for the few-shot NER task, dedicated to retrieving and reinforcing entity prototypes resilient to adversarial inference, thereby enhancing cross-domain semantic coherence. In particular, AAL employs a two-stage paradigm consisting of training and fine-tuning. The process initiates with augmentation learning by leveraging two kinds of prompt learning schemes, then identifies prototypes under the guidance of a variational manner. Furthermore, we devise a domain-oriented prototype refinement to optimize prototype learning under conditions of uncertainty attack, facilitating the effective transfer of common knowledge from source to target domains. The experimental results, encompassing the few-shot NER datasets under both certainty and uncertainty conditions, affirm the superiority of the proposed AAL over several representative baselines, particularly its capability against adversarial attacks.
CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder
PDF ↗Singing Voice Synthesis (SVS) aims to generate singing voices of high fidelity and expressiveness. Conventional SVS systems usually utilize an acoustic model to transform a music score into acoustic features, followed by a vocoder to reconstruct the singing voice. It was recently shown that end-to-end modeling is effective in the fields of SVS and Text to Speech (TTS). In this work, we thus present a fully end-to-end SVS method together with a chunkwise streaming inference to address the latency issue for practical usages. Note that this is the first attempt to fully implement end-to-end streaming audio synthesis using latent representations in VAE. We have made specific improvements to enhance the performance of streaming SVS using latent representations. Experimental results demonstrate that the proposed method achieves synthesized audio with high expressiveness and pitch accuracy in both streaming SVS and TTS tasks.
Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with eight state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets.
Multiple signal modalities, such as vision and sounds, are naturally present in real-world phenomena. Recently, there has been growing interest in learning generative models, in particular variational autoencoder (VAE), to for multimodal representation learning especially in the case of missing modalities. The primary goal of these models is to learn a modality-invariant and modality-specific representation that characterizes information across multiple modalities. Previous attempts at multimodal VAEs approach this mainly through the lens of experts, aggregating unimodal inference distributions with a product of experts (PoE), a mixture of experts (MoE), or a combination of both. In this paper, we provide an alternative generic and theoretical formulation of multimodal VAE through the lens of barycenter. We first show that PoE and MoE are specific instances of barycenters, derived by minimizing the asymmetric weighted KL divergence to unimodal inference distributions. Our novel formulation extends these two barycenters to a more flexible choice by considering different types of divergences. In particular, we explore the Wasserstein barycenter defined by the 2-Wasserstein distance, which better preserves the geometry of unimodal distributions by capturing both modality-specific and modality-invariant representations compared to KL divergence. Empirical studies on three multimodal benchmarks demonstrated the effectiveness of the proposed method.
Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriors
PDF ↗We propose denoising diffusion variational inference (DDVI), a black-box variational inference algorithm for latent variable models which relies on diffusion models as flexible approximate posteriors. Specifically, our method introduces an expressive class of diffusion-based variational posteriors that perform iterative refinement in latent space; we train these posteriors with a novel regularized evidence lower bound (ELBO) on the marginal likelihood inspired by the wake-sleep algorithm. Our method is easy to implement (it fits a regularized extension of the ELBO), is compatible with black-box variational inference, and outperforms alternative classes of approximate posteriors based on normalizing flows or adversarial networks. We find that DDVI improves inference and learning in deep latent variable models across common benchmarks as well as on a motivating task in biology---inferring latent ancestry from human genomes---where it outperforms strong baselines on the Thousand Genomes dataset.
A recent work introduces the problem of learning set functions from data generated by a so-called optimal subset oracle. Their approach approximates the underlying utility function with an energy-based model, whose parameters are estimated via mean-field variational inference. This approximation reduces to fixed point iterations; however, as the number of iterations increases, automatic differentiation quickly becomes computationally prohibitive due to the size of the Jacobians that are stacked during backpropagation. We address this challenge with implicit differentiation and examine the convergence conditions for the fixed-point iterations. We empirically demonstrate the efficiency of our method on synthetic and real-world subset selection applications including product recommendation, set anomaly detection and compound selection tasks.
Algebraic model counting unifies many inference tasks on logic formulas by exploiting semirings. Rather than focusing on inference, we consider learning, especially in statistical-relational and neurosymbolic AI, which combine logical, probabilistic and neural representations. Concretely, we show that the very same semiring perspective of algebraic model counting also applies to learning. This allows us to unify various learning algorithms by generalizing gradients and backpropagation to different semirings. Furthermore, we show how cancellation and ordering properties of a semiring can be exploited for more memory-efficient backpropagation. This allows us to obtain some interesting variations of state-of-the-art gradient-based optimisation methods for probabilistic logical models. We also discuss why algebraic model counting on tractable circuits does not lead to more efficient second-order optimization. Empirically, our algebraic backpropagation exhibits considerable speed-ups as compared to existing approaches.
With the advancement of pre-trained vision-language (VL) models, enhancing the alignment between visual and linguistic modalities in downstream tasks has emerged as a critical challenge. Different from existing fine-tuning methods that add extra modules to these two modalities, we investigate whether the frozen model can be fine-tuned by customized noise. Our approach is motivated by the scientific study of beneficial noise, namely Positive-incentive Noise (Pi-noise) , which quantitatively analyzes the impact of noise. It therefore implies a new scheme to learn beneficial noise distribution that can be employed to fine-tune VL models. Focusing on few-shot classification tasks based on CLIP, we reformulate the inference process of CLIP and apply variational inference, demonstrating how to generate Pi-noise towards visual and linguistic modalities. Then, we propose Positive-incentive Noise Injector (PiNI), which can fine-tune CLIP via injecting noise into both visual and text encoders. Since the proposed method can learn the distribution of beneficial noise, we can obtain more diverse embeddings of vision and language to better align these two modalities for specific downstream tasks within limited computational resources. We evaluate different noise incorporation approaches and network architectures of PiNI. The evaluation across 11 datasets demonstrates its effectiveness.
Diffusion models have achieved remarkable success in the image and video generation tasks. Nevertheless, they often require a large amount of memory and time overhead during inference, due to the complex network architecture and considerable number of timesteps for iterative diffusion. Recently, the post-training quantization (PTQ) technique has proved a promising way to reduce the inference cost by quantizing the float-point operations to low-bit ones. However, most of them fail to tackle with the large variations in the distribution of activations across distinct channels and timesteps, as well as the inconsistent of input between quantization and inference on diffusion models, thus leaving much room for improvement. To address the above issues, we propose a novel method dubbed Timestep-Channel Adaptive Quantization for Diffusion Models (TCAQ-DM). Specifically, we develop a timestep-channel joint reparameterization (TCR) module to balance the activation range along both the timesteps and channels, facilitating the successive reconstruction procedure. Subsequently, we employ a dynamically adaptive quantization (DAQ) module that mitigate the quantization error by selecting an optimal quantizer for each post-Softmax layers according to their specific types of distributions. Moreover, we present a progressively aligned reconstruction (PAR) strategy to mitigate the bias caused by the input mismatch. Extensive experiments on various benchmarks and distinct diffusion models demonstrate that the proposed method substantially outperforms the state-of-the-art approaches in most cases, especially yielding comparable FID metrics to the full precision model on CIFAR-10 in the W6A6 setting, while enabling generating available images in the W4A4 settings.
In recent years, deep multimodal learning has seen significant advancements. However, there remains a lack of multimodal fusion methods capable of dynamically adjusting the weighting of information both within and across modalities based on input samples. In the domain of multimodal intent recognition, the text modality often contains the most relevant information for intent detection, while the audio and visual modalities provide comparatively less critical information. There is a significant variation in the density of important information across different modalities and samples. To address this challenge, we propose a Dynamic Attention Allocation Fusion (DAF) method with an adaptive network structure that dynamically allocates attention both within individual modalities and across multiple modalities. This approach enables the model to focus more effectively on the most informative modalities and their respective internal features. Furthermore, we introduce a multi-view contrastive learning framework based on DAF (MVCL-DAF). This framework uses distinct and isolated modules to process information from various modalities, taking inspiration from the way the human brain processes multimodal information. Each modality independently infers intent using its respective module, while DAF integrates the multimodal information to produce a comprehensive global intent prediction. The text modality, functioning as the primary modality due to its rich semantic content, guides the other modules in the multi-view contrastive learning process. Extensive experiments demonstrate that our approach significantly outperforms existing state-of-the-art methods.
Mimicking the real interaction trajectory in the inference of the world model has been shown to improve the sample efficiency of model-based reinforcement learning (MBRL) algorithms. Many methods directly use known state sequences for reasoning. However, this approach fails to enhance the quality of reasoning by capturing the subtle variation between states. Much like how humans infer trends in event development from this variation, in this work, we introduce Global-Local variation Awareness Mamba-based world model (GLAM) that improves reasoning quality by perceiving and predicting variation between states. GLAM comprises two Mamba-based parallel reasoning modules, GMamba and LMamba, which focus on perceiving variation from global and local perspectives, respectively, during the reasoning process. GMamba focuses on identifying patterns of variation between states in the input sequence and leverages these patterns to enhance the prediction of future state variation. LMamba emphasizes reasoning about unknown information, such as rewards, termination signals, and visual representations, by perceiving variation in adjacent states. By integrating the strengths of the two modules, GLAM accounts for higher-value variation in environmental changes, providing the agent with more efficient imagination-based training. We demonstrate that our method outperforms existing methods in normalized human scores on the Atari 100k benchmark.
Variational autoencoder performs well in community detection on static networks, but it is difficult to directly extend to continuous dynamic networks. The main reason is that traditional methods mainly rely on adjacency structures to complete the inference and generation processes. However, continuous dynamic networks cannot be described by this structure because the inherent timeliness and causality information of the network would be lost. To address this issue, we propose a novel variational autoencoder, CT-VAE, for community detection in continuous dynamic networks, along with its scalable variant, CT-CAVAE. By conceptualizing node interactions as event streams and adopting the Hawkes process to capture temporal dynamics and causality, and incorporating them into the inference process, CT-VAE can effectively extend the traditional inference approach to continuous dynamic networks. Additionally, in the generation phase, CT-VAE combines pseudo-labeling and compact constraint strategies to facilitate the reconstruction process of non-adjacent structures. For the scalable variant, CT-CAVAE, end-to-end community detection is achieved by cleverly combining Gaussian mixture distribution. Extensive experimental results demonstrate that the proposed CT-VAE and CT-CAVAE achieve more favorable performance compared with the state-of-the-art baselines.
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.
Graph neural networks (GNNs) provide important prospective insights in applications such as social behavior analysis and financial risk analysis based on their powerful learning capabilities on graph data. Nevertheless, GNNs' predictive performance relies on the quality of task-specific node labels, so it is common practice to improve the model's generalization ability in the downstream execution of decision-making tasks through pre-training. Graph prompting is a prudent choice but risky without taking measures to prevent data leakage. In other words, in high-risk decision scenarios, prompt learning can infer private information by accessing model parameters trained on private data (publishing model parameters in pre-training, i.e., without directly leaking the raw data, is a tacitly accepted trend). However, myriad graph inference attacks necessitate tailored module design and processing to enhance inference capabilities due to variations in supervision signals. In this paper, we propose a novel Prompt-based unifying Inference Attack framework on GNNs, named ProIA. Specifically, ProIA retains the crucial topological information of the graph during pre-training, enhancing the background knowledge of the inference attack model. It then utilizes a unified prompt and introduces additional disentanglement factors in downstream attacks to adapt to task-relevant knowledge. Finally, extensive experiments show that ProIA enhances attack capabilities and demonstrates remarkable adaptability to various inference attacks.
PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement
PDF ↗Recent works on remote PhotoPlethysmoGraphy (rPPG) estimation typically use techniques like CNNs and Transformers to encode implicit features from facial videos for prediction. These methods learn to directly map facial videos to the static values of rPPG signals, overlooking the inherent dynamic characteristics of rPPG sequence. Moreover, the rPPG signal is extremely weak and highly susceptible to interference from various sources of noise, including illumination conditions, head movements, and variations in skin tone. To address these limitations, we propose a Physiology-based dynamicity disentangled diffusion (PhysDiff) model particularly designed for robust rPPG estimation. PhysDiff leverages the diffusion model to learn the distribution of quasi-periodic rPPG signal and uses a dynamicity disentanglement strategy to capture two dynamic characteristics in temporal rPPG signal, i.e., trend and amplitude. This disentanglement is motivated by the underlying dynamic physiological processes of vasodilation and vasoconstriction, ensuring a more precise representation of the rPPG signal. The disentangled components are then used as pivotal conditions in the proposed spatial-temporal hybrid denoiser for rPPG reconstruction. Besides, we introduce a periodicity-based multi-hypothesis selection strategy in model inference, which compares the natural periodicity of multiple generated rPPG hypotheses and selects the most favorable one as the final prediction. Extensive experiments on four datasets demonstrate that our PhysDiff significantly outperforms prior methods on both intra-dataset and cross-dataset testing.