PyTorchKR Papers

최신 논문

총 11,878편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2401.06209공식 코드 · Papers with Code

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Is vision good enough for language? Recent advancements in multimodal models primarily stem from the powerful reasoning abilities of large language models (LLMs). However, the visual component typically depends only on the instance-level contrastive language-image pre-training (CLIP). Our research reveals that the visual capabilities in recent multimodal LLMs (MLLMs) still exhibit systematic shortcomings. To understand the roots of these errors, we explore the gap between the visual embedding space of CLIP and vision-only self-supervised learning. We identify ''CLIP-blind pairs'' - images that CLIP perceives as similar despite their clear visual differences. With these pairs, we construct the Multimodal Visual Patterns (MMVP) benchmark. MMVP exposes areas where state-of-the-art systems, including GPT-4V, struggle with straightforward questions across nine basic visual patterns, often providing incorrect answers and hallucinated explanations. We further evaluate various CLIP-based vision-and-language models and found a notable correlation between visual patterns that challenge CLIP models and those problematic for multimodal LLMs. As an initial effort to address these issues, we propose a Mixture of Features (MoF) approach, demonstrating that integrating vision self-supervised learning features with MLLMs can significantly enhance their visual grounding capabilities. Together, our research suggests visual representation learning remains an open challenge, and accurate visual grounding is crucial for future successful multimodal systems.

arXiv:2401.06634

CCFC: Bridging Federated Clustering and Contrastive Learning

Federated clustering, an essential extension of centralized clustering for federated scenarios, enables multiple data-holding clients to collaboratively group data while keeping their data locally. In centralized scenarios, clustering driven by representation learning has made significant advancements in handling high-dimensional complex data. However, the combination of federated clustering and representation learning remains underexplored. To bridge this, we first tailor a cluster-contrastive model for learning clustering-friendly representations. Then, we harness this model as the foundation for proposing a new federated clustering method, named cluster-contrastive federated clustering (CCFC). Benefiting from representation learning, the clustering performance of CCFC even double those of the best baseline methods in some cases. Compared to the most related baseline, the benefit results in substantial NMI score improvements of up to 0.4155 on the most conspicuous case. Moreover, CCFC also shows superior performance in handling device failures from a practical viewpoint.

arXiv:2401.06557공식 코드 · Papers with Code

Treatment-Aware Hyperbolic Representation Learning for Causal Effect Estimation with Social Networks

Estimating the individual treatment effect (ITE) from observational data is a crucial research topic that holds significant value across multiple domains. How to identify hidden confounders poses a key challenge in ITE estimation. Recent studies have incorporated the structural information of social networks to tackle this challenge, achieving notable advancements. However, these methods utilize graph neural networks to learn the representation of hidden confounders in Euclidean space, disregarding two critical issues: (1) the social networks often exhibit a scalefree structure, while Euclidean embeddings suffer from high distortion when used to embed such graphs, and (2) each ego-centric network within a social network manifests a treatment-related characteristic, implying significant patterns of hidden confounders. To address these issues, we propose a novel method called Treatment-Aware Hyperbolic Representation Learning (TAHyper). Firstly, TAHyper employs the hyperbolic space to encode the social networks, thereby effectively reducing the distortion of confounder representation caused by Euclidean embeddings. Secondly, we design a treatment-aware relationship identification module that enhances the representation of hidden confounders by identifying whether an individual and her neighbors receive the same treatment. Extensive experiments on two benchmark datasets are conducted to demonstrate the superiority of our method.

arXiv:2401.05430공식 코드 · Papers with Code

Multi-relational Graph Diffusion Neural Network with Parallel Retention for Stock Trends Classification

Stock trend classification remains a fundamental yet challenging task, owing to the intricate time-evolving dynamics between and within stocks. To tackle these two challenges, we propose a graph-based representation learning approach aimed at predicting the future movements of multiple stocks. Initially, we model the complex time-varying relationships between stocks by generating dynamic multi-relational stock graphs. This is achieved through a novel edge generation algorithm that leverages information entropy and signal energy to quantify the intensity and directionality of inter-stock relations on each trading day. Then, we further refine these initial graphs through a stochastic multi-relational diffusion process, adaptively learning task-optimal edges. Subsequently, we implement a decoupled representation learning scheme with parallel retention to obtain the final graph representation. This strategy better captures the unique temporal features within individual stocks while also capturing the overall structure of the stock graph. Comprehensive experiments conducted on real-world datasets from two US markets (NASDAQ and NYSE) and one Chinese market (Shanghai Stock Exchange: SSE) validate the effectiveness of our method. Our approach consistently outperforms state-of-the-art baselines in forecasting next trading day stock trends across three test periods spanning seven years. Datasets and code have been released (https://github.com/pixelhero98/MGDPR).

arXiv:2401.05373

Dynamic Spiking Framework for Graph Neural Networks

The integration of Spiking Neural Networks (SNNs) and Graph Neural Networks (GNNs) is gradually attracting attention due to the low power consumption and high efficiency in processing the non-Euclidean data represented by graphs. However, as a common problem, dynamic graph representation learning faces challenges such as high complexity and large memory overheads. Current work often uses SNNs instead of Recurrent Neural Networks (RNNs) by using binary features instead of continuous ones for efficient training, which would overlooks graph structure information and leads to the loss of details during propagation. Additionally, optimizing dynamic spiking models typically requires propagation of information across time steps, which increases memory requirements. To address these challenges, we present a framework named \underline{Dy}namic \underline{S}p\underline{i}king \underline{G}raph \underline{N}eural Networks (\method{}). To mitigate the information loss problem, \method{} propagates early-layer information directly to the last layer for information compensation. To accommodate the memory requirements, we apply the implicit differentiation on the equilibrium state, which does not rely on the exact reverse of the forward computation. While traditional implicit differentiation methods are usually used for static situations, \method{} extends it to the dynamic graph setting. Extensive experiments on three large-scale real-world dynamic graph datasets validate the effectiveness of \method{} on dynamic node classification tasks with lower computational costs.

arXiv:2401.05698공식 코드 · Papers with Code

HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition

Audio-Visual Emotion Recognition (AVER) has garnered increasing attention in recent years for its critical role in creating emotion-ware intelligent machines. Previous efforts in this area are dominated by the supervised learning paradigm. Despite significant progress, supervised learning is meeting its bottleneck due to the longstanding data scarcity issue in AVER. Motivated by recent advances in self-supervised learning, we propose Hierarchical Contrastive Masked Autoencoder (HiCMAE), a novel self-supervised framework that leverages large-scale self-supervised pre-training on vast unlabeled audio-visual data to promote the advancement of AVER. Following prior arts in self-supervised audio-visual representation learning, HiCMAE adopts two primary forms of self-supervision for pre-training, namely masked data modeling and contrastive learning. Unlike them which focus exclusively on top-layer representations while neglecting explicit guidance of intermediate layers, HiCMAE develops a three-pronged strategy to foster hierarchical audio-visual feature learning and improve the overall quality of learned representations. To verify the effectiveness of HiCMAE, we conduct extensive experiments on 9 datasets covering both categorical and dimensional AVER tasks. Experimental results show that our method significantly outperforms state-of-the-art supervised and self-supervised audio-visual methods, which indicates that HiCMAE is a powerful audio-visual emotion representation learner. Codes and models will be publicly available at https://github.com/sunlicai/HiCMAE.

arXiv:2401.05437

Representation Learning for Wearable-Based Applications in the Case of Missing Data

Wearable devices continuously collect sensor data and use it to infer an individual's behavior, such as sleep, physical activity, and emotions. Despite the significant interest and advancements in this field, modeling multimodal sensor data in real-world environments is still challenging due to low data quality and limited data annotations. In this work, we investigate representation learning for imputing missing wearable data and compare it with state-of-the-art statistical approaches. We investigate the performance of the transformer model on 10 physiological and behavioral signals with different masking ratios. Our results show that transformers outperform baselines for missing data imputation of signals that change more frequently, but not for monotonic signals. We further investigate the impact of imputation strategies and masking rations on downstream classification tasks. Our study provides insights for the design and development of masking-based self-supervised learning tasks and advocates the adoption of hybrid-based imputation strategies to address the challenge of missing data in wearable devices.

arXiv:2401.05431

TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing

Representation learning frameworks in unlabeled time series have been proposed for medical signal processing. Despite the numerous excellent progresses have been made in previous works, we observe the representation extracted for the time series still does not generalize well. In this paper, we present a Time series (medical signal) Representation Learning framework via Spectrogram (TRLS) to get more informative representations. We transform the input time-domain medical signals into spectrograms and design a time-frequency encoder named Time Frequency RNN (TFRNN) to capture more robust multi-scale representations from the augmented spectrograms. Our TRLS takes spectrogram as input with two types of different data augmentations and maximizes the similarity between positive ones, which effectively circumvents the problem of designing negative samples. Our evaluation of four real-world medical signal datasets focusing on medical signal classification shows that TRLS is superior to the existing frameworks.

arXiv:2401.05975공식 코드 · Papers with Code

End-to-end Learnable Clustering for Intent Learning in Recommendation

Intent learning, which aims to learn users' intents for user understanding and item recommendation, has become a hot research spot in recent years. However, existing methods suffer from complex and cumbersome alternating optimization, limiting performance and scalability. To this end, we propose a novel intent learning method termed \underline{ELCRec}, by unifying behavior representation learning into an \underline{E}nd-to-end \underline{L}earnable \underline{C}lustering framework, for effective and efficient \underline{Rec}ommendation. Concretely, we encode user behavior sequences and initialize the cluster centers (latent intents) as learnable neurons. Then, we design a novel learnable clustering module to separate different cluster centers, thus decoupling users' complex intents. Meanwhile, it guides the network to learn intents from behaviors by forcing behavior embeddings close to cluster centers. This allows simultaneous optimization of recommendation and clustering via mini-batch data. Moreover, we propose intent-assisted contrastive learning by using cluster centers as self-supervision signals, further enhancing mutual promotion. Both experimental results and theoretical analyses demonstrate the superiority of ELCRec from six perspectives. Compared to the runner-up, ELCRec improves NDCG@5 by 8.9\% and reduces computational costs by 22.5\% on the Beauty dataset. Furthermore, due to the scalability and universal applicability, we deploy this method on the industrial recommendation system with 130 million page views and achieve promising results. The codes are available on GitHub (https://github.com/yueliu1999/ELCRec). A collection (papers, codes, datasets) of deep group recommendation/intent learning methods is available on GitHub (https://github.com/yueliu1999/Awesome-Deep-Group-Recommendation).

arXiv:2401.05730

Enhancing Contrastive Learning with Efficient Combinatorial Positive Pairing

In the past few years, contrastive learning has played a central role for the success of visual unsupervised representation learning. Around the same time, high-performance non-contrastive learning methods have been developed as well. While most of the works utilize only two views, we carefully review the existing multi-view methods and propose a general multi-view strategy that can improve learning speed and performance of any contrastive or non-contrastive method. We first analyze CMC's full-graph paradigm and empirically show that the learning speed of $K$-views can be increased by $_{K}\mathrm{C}_{2}$ times for small learning rate and early training. Then, we upgrade CMC's full-graph by mixing views created by a crop-only augmentation, adopting small-size views as in SwAV multi-crop, and modifying the negative sampling. The resulting multi-view strategy is called ECPP (Efficient Combinatorial Positive Pairing). We investigate the effectiveness of ECPP by applying it to SimCLR and assessing the linear evaluation performance for CIFAR-10 and ImageNet-100. For each benchmark, we achieve a state-of-the-art performance. In case of ImageNet-100, ECPP boosted SimCLR outperforms supervised learning.

arXiv:2401.04914공식 코드 · Papers with Code

DualVAE: Dual Disentangled Variational AutoEncoder for Recommendation

Learning precise representations of users and items to fit observed interaction data is the fundamental task of collaborative filtering. Existing studies usually infer entangled representations to fit such interaction data, neglecting to model the diverse matching relationships between users and items behind their interactions, leading to limited performance and weak interpretability. To address this problem, we propose a Dual Disentangled Variational AutoEncoder (DualVAE) for collaborative recommendation, which combines disentangled representation learning with variational inference to facilitate the generation of implicit interaction data. Specifically, we first implement the disentangling concept by unifying an attention-aware dual disentanglement and disentangled variational autoencoder to infer the disentangled latent representations of users and items. Further, to encourage the correspondence and independence of disentangled representations of users and items, we design a neighborhood-enhanced representation constraint with a customized contrastive mechanism to improve the representation quality. Extensive experiments on three real-world benchmarks show that our proposed model significantly outperforms several recent state-of-the-art baselines. Further empirical experimental results also illustrate the interpretability of the disentangled representations learned by DualVAE.

arXiv:2401.05064공식 코드 · Papers with Code

Singer Identity Representation Learning using Self-Supervised Techniques

Significant strides have been made in creating voice identity representations using speech data. However, the same level of progress has not been achieved for singing voices. To bridge this gap, we suggest a framework for training singer identity encoders to extract representations suitable for various singing-related tasks, such as singing voice similarity and synthesis. We explore different self-supervised learning techniques on a large collection of isolated vocal tracks and apply data augmentations during training to ensure that the representations are invariant to pitch and content variations. We evaluate the quality of the resulting representations on singer similarity and identification tasks across multiple datasets, with a particular emphasis on out-of-domain generalization. Our proposed framework produces high-quality embeddings that outperform both speaker verification and wav2vec 2.0 pre-trained baselines on singing voice while operating at 44.1 kHz. We release our code and trained models to facilitate further research on singing voice and related areas.

arXiv:2401.04860공식 코드 · Papers with Code

Modality-Aware Representation Learning for Zero-shot Sketch-based Image Retrieval

Zero-shot learning offers an efficient solution for a machine learning model to treat unseen categories, avoiding exhaustive data collection. Zero-shot Sketch-based Image Retrieval (ZS-SBIR) simulates real-world scenarios where it is hard and costly to collect paired sketch-photo samples. We propose a novel framework that indirectly aligns sketches and photos by contrasting them through texts, removing the necessity of access to sketch-photo pairs. With an explicit modality encoding learned from data, our approach disentangles modality-agnostic semantics from modality-specific information, bridging the modality gap and enabling effective cross-modal content retrieval within a joint latent space. From comprehensive experiments, we verify the efficacy of the proposed model on ZS-SBIR, and it can be also applied to generalized and fine-grained settings.

arXiv:2401.04354

Knowledge-enhanced Multi-perspective Video Representation Learning for Scene Recognition

With the explosive growth of video data in real-world applications, a comprehensive representation of videos becomes increasingly important. In this paper, we address the problem of video scene recognition, whose goal is to learn a high-level video representation to classify scenes in videos. Due to the diversity and complexity of video contents in realistic scenarios, this task remains a challenge. Most existing works identify scenes for videos only from visual or textual information in a temporal perspective, ignoring the valuable information hidden in single frames, while several earlier studies only recognize scenes for separate images in a non-temporal perspective. We argue that these two perspectives are both meaningful for this task and complementary to each other, meanwhile, externally introduced knowledge can also promote the comprehension of videos. We propose a novel two-stream framework to model video representations from multiple perspectives, i.e. temporal and non-temporal perspectives, and integrate the two perspectives in an end-to-end manner by self-distillation. Besides, we design a knowledge-enhanced feature fusion and label prediction method that contributes to naturally introducing knowledge into the task of video scene recognition. Experiments conducted on a real-world dataset demonstrate the effectiveness of our proposed method.

arXiv:2401.02971

Deep Anomaly Detection in Text

Deep anomaly detection methods have become increasingly popular in recent years, with methods like Stacked Autoencoders, Variational Autoencoders, and Generative Adversarial Networks greatly improving the state-of-the-art. Other methods rely on augmenting classical models (such as the One-Class Support Vector Machine), by learning an appropriate kernel function using Neural Networks. Recent developments in representation learning by self-supervision are proving to be very beneficial in the context of anomaly detection. Inspired by the advancements in anomaly detection using self-supervised learning in the field of computer vision, this thesis aims to develop a method for detecting anomalies by exploiting pretext tasks tailored for text corpora. This approach greatly improves the state-of-the-art on two datasets, 20Newsgroups, and AG News, for both semi-supervised and unsupervised anomaly detection, thus proving the potential for self-supervised anomaly detectors in the field of natural language processing.

arXiv:2401.03563

Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning

Recently, multi-task instruction tuning has been applied into sentence representation learning, which endows the capability of generating specific representations with the guidance of task instruction, exhibiting strong generalization ability on new tasks. However, these methods mostly neglect the potential interference problems across different tasks and instances, which may affect the training and convergence of the model. To address it, we propose a data curriculum method, namely Data-CUBE, that arranges the orders of all the multi-task data for training, to minimize the interference risks from the two views. In the task level, we aim to find the optimal task order to minimize the total cross-task interference risk, which is exactly the traveling salesman problem, hence we utilize a simulated annealing algorithm to find its solution. In the instance level, we measure the difficulty of all instances per task, then divide them into the easy-to-difficult mini-batches for training. Experiments on MTEB sentence representation evaluation tasks show that our approach can boost the performance of state-of-the-art methods. Our code and data are publicly available at the link: \url{https://github.com/RUCAIBox/Data-CUBE}.

arXiv:2401.03420

Channel Mapping Based on Interleaved Learning with Complex-Domain MLP-Mixer

In multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) systems, representing the whole channel only based on partial subchannels will significantly reduce the channel acquisition overhead. For such a channel mapping task, inspired by the intrinsic coupling across the space and frequency domains, this letter proposes to use interleaved learning with partial antenna and subcarrier characteristics to represent the whole MIMO-OFDM channel. Specifically, we design a complex-domain multilayer perceptron (MLP)-Mixer (CMixer), which utilizes two kinds of complex-domain MLP modules to learn the space and frequency characteristics respectively and then interleaves them to couple the learned properties. The complex-domain computation facilitates the learning on the complex-valued channel data, while the interleaving tightens the coupling of space and frequency domains. These two designs jointly reduce the learning burden, making the physics-inspired CMixer more effective on channel representation learning than existing data-driven approaches. Simulation shows that the proposed scheme brings 4.6~10dB gains in mapping accuracy compared to existing schemes under different settings. Besides, ablation studies show the necessity of complex-domain computation as well as the extent to which the interleaved learning matches the channel properties.

arXiv:2401.03321

PIXAR: Auto-Regressive Language Modeling in Pixel Space

Recent work showed the possibility of building open-vocabulary large language models (LLMs) that directly operate on pixel representations. These models are implemented as autoencoders that reconstruct masked patches of rendered text. However, these pixel-based LLMs are limited to discriminative tasks (e.g., classification) and, similar to BERT, cannot be used to generate text. Therefore, they cannot be used for generative tasks such as free-form question answering. In this work, we introduce PIXAR, the first pixel-based autoregressive LLM that performs text generation. Consisting of only a decoder, PIXAR can perform free-form generative tasks while keeping the number of parameters on par with previous encoder-decoder models. Furthermore, we highlight the challenges of generating text as non-noisy images and show this is due to using a maximum likelihood objective. To overcome this problem, we propose an adversarial pretraining stage that improves the readability and accuracy of PIXAR by 8.1 on LAMBADA and 8.5 on bAbI -- making it comparable to GPT-2 on text generation tasks. This paves the way to build open-vocabulary LLMs that operate on perceptual input only and calls into question the necessity of the usual symbolic input representation, i.e., text as (sub)tokens.

arXiv:2401.03597

Few-Shot Causal Representation Learning for Out-of-Distribution Generalization on Heterogeneous Graphs

Heterogeneous graph few-shot learning (HGFL) has been developed to address the label sparsity issue in heterogeneous graphs (HGs), which consist of various types of nodes and edges. The core concept of HGFL is to extract knowledge from rich-labeled classes in a source HG, transfer this knowledge to a target HG to facilitate learning new classes with few-labeled training data, and finally make predictions on unlabeled testing data. Existing methods typically assume that the source HG, training data, and testing data all share the same distribution. However, in practice, distribution shifts among these three types of data are inevitable due to two reasons: (1) the limited availability of the source HG that matches the target HG distribution, and (2) the unpredictable data generation mechanism of the target HG. Such distribution shifts result in ineffective knowledge transfer and poor learning performance in existing methods, thereby leading to a novel problem of out-of-distribution (OOD) generalization in HGFL. To address this challenging problem, we propose a novel Causal OOD Heterogeneous graph Few-shot learning model, namely COHF. In COHF, we first characterize distribution shifts in HGs with a structural causal model, establishing an invariance principle for OOD generalization in HGFL. Then, following this invariance principle, we propose a new variational autoencoder-based heterogeneous graph neural network to mitigate the impact of distribution shifts. Finally, by integrating this network with a novel meta-learning framework, COHF effectively transfers knowledge to the target HG to predict new classes with few-labeled data. Extensive experiments on seven real-world datasets have demonstrated the superior performance of COHF over the state-of-the-art methods.

arXiv:2401.03369공식 코드 · Papers with Code

Multi-Modal Representation Learning for Molecular Property Prediction: Sequence, Graph, Geometry

Molecular property prediction refers to the task of labeling molecules with some biochemical properties, playing a pivotal role in the drug discovery and design process. Recently, with the advancement of machine learning, deep learning-based molecular property prediction has emerged as a solution to the resource-intensive nature of traditional methods, garnering significant attention. Among them, molecular representation learning is the key factor for molecular property prediction performance. And there are lots of sequence-based, graph-based, and geometry-based methods that have been proposed. However, the majority of existing studies focus solely on one modality for learning molecular representations, failing to comprehensively capture molecular characteristics and information. In this paper, a novel multi-modal representation learning model, which integrates the sequence, graph, and geometry characteristics, is proposed for molecular property prediction, called SGGRL. Specifically, we design a fusion layer to fusion the representation of different modalities. Furthermore, to ensure consistency across modalities, SGGRL is trained to maximize the similarity of representations for the same molecule while minimizing similarity for different molecules. To verify the effectiveness of SGGRL, seven molecular datasets, and several baselines are used for evaluation and comparison. The experimental results demonstrate that SGGRL consistently outperforms the baselines in most cases. This further underscores the capability of SGGRL to comprehensively capture molecular information. Overall, the proposed SGGRL model showcases its potential to revolutionize molecular property prediction by leveraging multi-modal representation learning to extract diverse and comprehensive molecular insights. Our code is released at https://github.com/Vencent-Won/SGGRL.