Multi-view representation learning integrates multiple observable views of an entity into a unified representation to facilitate downstream tasks. Current methods predominantly focus on distinguishing compatible components across views, followed by a single-step parallel fusion process. However, this parallel fusion is static in essence, overlooking potential conflicts among views and compromising representation ability. To address this issue, this paper proposes a novel Sequential fusion framework for Multi-view Representation Learning, termed SeqMvRL. Specifically, we model multi-view fusion as a sequential decision-making problem and construct a pairwise integrator (PI) and a next-view selector (NVS), which represent the environment and agent in reinforcement learning, respectively. PI merges the current fused feature with the selected view, while NVS is introduced to determine which view to fuse subsequently. By adaptively selecting the next optimal view for fusion based on the current fusion state, SeqMvRL thereby effectively reduces conflicts and enhances unified representation quality. Additionally, an elaborate novel reward function encourages the model to prioritize views that enhance the discriminability of the fused features. Experimental results demonstrate that SeqMvRL outperforms parallel fusion schemes in classification and clustering tasks.

Meta-learning methods typically follow a two-loop framework, where each loop potentially suffers from notorious overfitting, hindering rapid adaptation and generalization to new tasks. Existing methods address this by enhancing the mutual-exclusivity or diversity of training samples, but these data manipulation strategies are data-dependent and insufficiently flexible. This work proposes a data-independent Meta-Gradient Augmentation (MGAug) method from the perspective of gradient regularization. The key idea is first to break the rote memories by network pruning to address memorization overfitting in the inner loop, then use the gradients of pruned sub-networks to augment meta-gradients, alleviating overfitting in the outer loop. Specifically, we explore three pruning strategies, including random width pruning, random parameter pruning, and a newly proposed catfish pruning that measures a Meta-Memorization Carrying Amount (MMCA) score for each parameter and prunes high-score ones to break rote memories. The proposed MGAug is theoretically guaranteed by the generalization bound from the PAC-Bayes framework. Extensive experiments on multiple few-shot learning benchmarks validate MGAug's effectiveness and significant improvement over various meta-baselines.

Deep multi-view subspace clustering aims to reveal a common subspace structure by exploiting rich multi-view information. Despite promising progress, current methods focus only on multi-view consistency and complementarity, often overlooking the adverse influence of entangled superfluous information in features. Moreover, most existing works lack scalability and are inefficient for large-scale scenarios. To this end, we innovatively propose a deep subspace clustering method via Multi-view Feature Decoupling (MvFD). First, MvFD incorporates well-designed multi-type auto-encoders with self-supervised learning, explicitly decoupling consistent, complementary, and superfluous features for every view. The disentangled and interpretable feature space can then better serve unified representation learning. By integrating these three types of information within a unified framework, we employ information theory to obtain a minimal and sufficient representation with high discriminability. Besides, we introduce a deep metric network to model self-expression correlation more efficiently, where network parameters remain unaffected by changes in sample numbers. Extensive experiments show that MvFD yields State-of-the-Art performance in various types of multi-view datasets.

Multivariate time series (MTS) forecasting is considered as a challenging task due to complex and nonlinear interdependencies between time steps and series. With the advance of deep learning, significant efforts have been made to model long-term and short-term temporal patterns hidden in historical information by recurrent neural networks (RNNs) with a temporal attention mechanism. Although various forecasting models have been developed, most of them are single-scale oriented, resulting in scale information loss. In this article, we seamlessly integrate multiscale analysis into deep learning frameworks to build scale-aware recurrent networks and propose two multiscale recurrent network (MRN) models for MTS forecasting. The first model called MRN-SA adopts a scale attention mechanism to dynamically select the most relevant information from different scales and simultaneously employs input attention and temporal attention to make predictions. The second one named as MRN-CSG introduces a novel cross-scale guidance mechanism to exploit the information from coarse scale to guide the decoding process at fine scale, which results in a lightweight and more easily trained model without obvious loss of accuracy. Extensive experimental results demonstrate that both MRN-SA and MRN-CSG can achieve state-of-the-art performance on five typical MTS datasets in different domains. The source codes will be publicly available at https://github.com/qguo2010/MRN.

Existing multi-view representation learning methods typically follow a specific-to-uniform pipeline, extracting latent features from each view and then fusing or aligning them to obtain the unified object representation. However, the manually pre-specified fusion functions and aligning criteria could potentially degrade the quality of the derived representation. To overcome them, we propose a novel uniform-to-specific multi-view learning framework from a meta-learning perspective, where the unified representation no longer involves manual manipulation but is automatically derived from a meta-learner named MetaViewer. Specifically, we formulated the extraction and fusion of view-specific latent features as a nested optimization problem and solved it by using a bi-level optimization scheme. In this way, MetaViewer automatically fuses view-specific features into a unified one and learns the optimal fusion scheme by observing reconstruction processes from the unified to the specific over all views. Extensive experimental results in downstream classification and clustering tasks demonstrate the efficiency and effectiveness of the proposed method.

Learning with noisy labels (LNL) aims to ensure model generalization given a label-corrupted training set. In this work, we investigate a rarely studied scenario of LNL on fine-grained datasets (LNL-FG), which is more practical and challenging as large inter-class ambiguities among fine-grained classes cause more noisy labels. We empirically show that existing methods that work well for LNL fail to achieve satisfying performance for LNL-FG, arising the practical need of effective solutions for LNL-FG. To this end, we propose a novel framework called stochastic noise-tolerated supervised contrastive learning (SNSCL) that confronts label noise by encouraging distinguishable representation. Specifically, we design a noise-tolerated supervised contrastive learning loss that incorporates a weight-aware mechanism for noisy label correction and selectively updating momentum queue lists. By this mechanism, we mitigate the effects of noisy anchors and avoid inserting noisy labels into the momentum-updated queue. Besides, to avoid manually-defined augmentation strategies in contrastive learning, we propose an efficient stochastic module that samples feature embeddings from a generated distribution, which can also enhance the representation ability of deep models. SNSCL is general and compatible with prevailing robust LNL strategies to improve their performance for LNL-FG. Extensive experiments demonstrate the effectiveness of SNSCL.

Multi-view (representation) learning derives an entity's representation from its multiple observable views to facilitate various downstream tasks. The most challenging topic is how to model unobserved entities and their relationships to specific views. To this end, this work proposes a novel multi-view learning method using a View-Aware parameter Modulation mechanism, termed VAM. The key idea is to use trainable parameters as proxies for unobserved entities and views, such that modeling entity-view relationships is converted into modeling the relationship between proxy parameters. Specifically, we first build a set of trainable parameters to learn a mapping from multi-view data to the unified representation as the entity proxy. Then we learn a prototype for each view and design a Modulation Parameter Generator (MPG) that learns a set of view-aware scale and shift parameters from prototypes to modulate the entity proxy and obtain view proxies. By constraining the representativeness, uniqueness, and simplicity of the proxies and proposing an entity-view contrastive loss, parameters are alternatively updated. We end up with a set of discriminative prototypes, view proxies, and an entity proxy that are flexible enough to yield robust representations for out-of-sample entities. Extensive experiments on five datasets show that the results of our VAM outperform existing methods in both classification and clustering tasks.