Large-scale vision-language pre-training has shown promising advances on various downstream tasks and achieved significant performance in multi-modal understanding and generation tasks. However, existing methods often perform poorly on image-text matching tasks that require a detailed semantics understanding of the text. Although there have been some works on this problem, they do not sufficiently exploit the structural knowledge present in sentences to enhance multi-modal language representations, which leads to poor performance. In this paper, we present an end-to-end framework Structure-CLIP, which integrates latent detailed semantics from the text to enhance fine-grained semantic representations. Specifically, (1) we use scene graphs in order to pay more attention to the detailed semantic learning in the text and fully explore structured knowledge between fine-grained semantics, and (2) we utilize the knowledge-enhanced framework with the help of the scene graph to make full use of representations of structured knowledge. To verify the effectiveness of our proposed method, we pre-trained our models with the aforementioned approach and conduct experiments on different downstream tasks. Numerical results show that Structure-CLIP can often achieve state-of-the-art performance on both VG-Attribution and VG-Relation datasets. Extensive experiments show its components are effective and its predictions are interpretable, which proves that our proposed method can enhance detailed semantic representation well.
相關內容
通(tong)過(guo)學習、實踐或探索所獲(huo)得的認識、判斷或技(ji)能(neng)。
Multi-view clustering has attracted broad attention due to its capacity to utilize consistent and complementary information among views. Although tremendous progress has been made recently, most existing methods undergo high complexity, preventing them from being applied to large-scale tasks. Multi-view clustering via matrix factorization is a representative to address this issue. However, most of them map the data matrices into a fixed dimension, limiting the model's expressiveness. Moreover, a range of methods suffers from a two-step process, i.e., multimodal learning and the subsequent $k$-means, inevitably causing a sub-optimal clustering result. In light of this, we propose a one-step multi-view clustering with diverse representation method, which incorporates multi-view learning and $k$-means into a unified framework. Specifically, we first project original data matrices into various latent spaces to attain comprehensive information and auto-weight them in a self-supervised manner. Then we directly use the information matrices under diverse dimensions to obtain consensus discrete clustering labels. The unified work of representation learning and clustering boosts the quality of the final results. Furthermore, we develop an efficient optimization algorithm with proven convergence to solve the resultant problem. Comprehensive experiments on various datasets demonstrate the promising clustering performance of our proposed method.
Although data-driven methods usually have noticeable performance on disease diagnosis and treatment, they are suspected of leakage of privacy due to collecting data for model training. Recently, federated learning provides a secure and trustable alternative to collaboratively train model without any exchange of medical data among multiple institutes. Therefore, it has draw much attention due to its natural merit on privacy protection. However, when heterogenous medical data exists between different hospitals, federated learning usually has to face with degradation of performance. In the paper, we propose a new personalized framework of federated learning to handle the problem. It successfully yields personalized models based on awareness of similarity between local data, and achieves better tradeoff between generalization and personalization than existing methods. After that, we further design a differentially sparse regularizer to improve communication efficiency during procedure of model training. Additionally, we propose an effective method to reduce the computational cost, which improves computation efficiency significantly. Furthermore, we collect 5 real medical datasets, including 2 public medical image datasets and 3 private multi-center clinical diagnosis datasets, and evaluate its performance by conducting nodule classification, tumor segmentation, and clinical risk prediction tasks. Comparing with 13 existing related methods, the proposed method successfully achieves the best model performance, and meanwhile up to 60% improvement of communication efficiency. Source code is public, and can be accessed at: //github.com/ApplicationTechnologyOfMedicalBigData/pFedNet-code.
Knowledge graph embedding (KGE) that maps entities and relations into vector representations is essential for downstream tasks. Conventional KGE methods require relatively high-dimensional entity representations to preserve the structural information of knowledge graph, but lead to oversized model parameters. Recent methods reduce model parameters by adopting low-dimensional entity representations, while developing techniques (e.g., knowledge distillation) to compensate for the reduced dimension. However, such operations produce degraded model accuracy and limited reduction of model parameters. Specifically, we view the concatenation of all entity representations as an embedding layer, and then conventional KGE methods that adopt high-dimensional entity representations equal to enlarging the width of the embedding layer to gain expressiveness. To achieve parameter efficiency without sacrificing accuracy, we instead increase the depth and propose a deeper embedding network for entity representations, i.e., a narrow embedding layer and a multi-layer dimension lifting network (LiftNet). Experiments on three public datasets show that the proposed method (implemented based on TransE and DistMult) with 4-dimensional entity representations achieves more accurate link prediction results than counterpart parameter-efficient KGE methods and strong KGE baselines, including TransE and DistMult with 512-dimensional entity representations.
Recent research in representation learning utilizes large databases of proteins or molecules to acquire knowledge of drug and protein structures through unsupervised learning techniques. These pre-trained representations have proven to significantly enhance the accuracy of subsequent tasks, such as predicting the affinity between drugs and target proteins. In this study, we demonstrate that by incorporating knowledge graphs from diverse sources and modalities into the sequences or SMILES representation, we can further enrich the representation and achieve state-of-the-art results on established benchmark datasets. We provide preprocessed and integrated data obtained from 7 public sources, which encompass over 30M triples. Additionally, we make available the pre-trained models based on this data, along with the reported outcomes of their performance on three widely-used benchmark datasets for drug-target binding affinity prediction found in the Therapeutic Data Commons (TDC) benchmarks. Additionally, we make the source code for training models on benchmark datasets publicly available. Our objective in releasing these pre-trained models, accompanied by clean data for model pretraining and benchmark results, is to encourage research in knowledge-enhanced representation learning.
Time-to-event (TTE) models are used in medicine and other fields for estimating the probability distribution of the time until a specific event occurs. TTE models provide many advantages over classification using fixed time horizons, including naturally handling censored observations, but require more parameters and are challenging to train in settings with limited labeled data. Existing approaches, e.g. proportional hazards or accelerated failure time, employ distributional assumptions to reduce parameters but are vulnerable to model misspecification. In this work, we address these challenges with MOTOR (Many Outcome Time Oriented Representations), a self-supervised model that leverages temporal structure found in collections of timestamped events in electronic health records (EHR) and health insurance claims. MOTOR uses a TTE pretraining objective that predicts the probability distribution of times when events occur, making it well-suited to transfer learning for medical prediction tasks. Having pretrained on EHR and claims data of up to 55M patient records (9B clinical events), we evaluate performance after finetuning for 19 tasks across two datasets. Task-specific models built using MOTOR improve time-dependent C statistics by 4.6% over state-of-the-art while greatly improving sample efficiency, achieving comparable performance to existing methods using only 5% of available task data.
Contrastive loss has been increasingly used in learning representations from multiple modalities. In the limit, the nature of the contrastive loss encourages modalities to exactly match each other in the latent space. Yet it remains an open question how the modality alignment affects the downstream task performance. In this paper, based on an information-theoretic argument, we first prove that exact modality alignment is sub-optimal in general for downstream prediction tasks. Hence we advocate that the key of better performance lies in meaningful latent modality structures instead of perfect modality alignment. To this end, we propose three general approaches to construct latent modality structures. Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization. Extensive experiments are conducted on two popular multi-modal representation learning frameworks: the CLIP-based two-tower model and the ALBEF-based fusion model. We test our model on a variety of tasks including zero/few-shot image classification, image-text retrieval, visual question answering, visual reasoning, and visual entailment. Our method achieves consistent improvements over existing methods, demonstrating the effectiveness and generalizability of our proposed approach on latent modality structure regularization.
We propose a knowledge-enhanced approach, ERNIE-ViL, to learn joint representations of vision and language. ERNIE-ViL tries to construct the detailed semantic connections (objects, attributes of objects and relationships between objects in visual scenes) across vision and language, which are essential to vision-language cross-modal tasks. Incorporating knowledge from scene graphs, ERNIE-ViL constructs Scene Graph Prediction tasks, i.e., Object Prediction, Attribute Prediction and Relationship Prediction in the pre-training phase. More specifically, these prediction tasks are implemented by predicting nodes of different types in the scene graph parsed from the sentence. Thus, ERNIE-ViL can model the joint representation characterizing the alignments of the detailed semantics across vision and language. Pre-trained on two large image-text alignment datasets (Conceptual Captions and SBU), ERNIE-ViL learns better and more robust joint representations. It achieves state-of-the-art performance on 5 vision-language downstream tasks after fine-tuning ERNIE-ViL. Furthermore, it ranked the 1st place on the VCR leader-board with an absolute improvement of 3.7%.
Automatic KB completion for commonsense knowledge graphs (e.g., ATOMIC and ConceptNet) poses unique challenges compared to the much studied conventional knowledge bases (e.g., Freebase). Commonsense knowledge graphs use free-form text to represent nodes, resulting in orders of magnitude more nodes compared to conventional KBs (18x more nodes in ATOMIC compared to Freebase (FB15K-237)). Importantly, this implies significantly sparser graph structures - a major challenge for existing KB completion methods that assume densely connected graphs over a relatively smaller set of nodes. In this paper, we present novel KB completion models that can address these challenges by exploiting the structural and semantic context of nodes. Specifically, we investigate two key ideas: (1) learning from local graph structure, using graph convolutional networks and automatic graph densification and (2) transfer learning from pre-trained language models to knowledge graphs for enhanced contextual representation of knowledge. We describe our method to incorporate information from both these sources in a joint model and provide the first empirical results for KB completion on ATOMIC and evaluation with ranking metrics on ConceptNet. Our results demonstrate the effectiveness of language model representations in boosting link prediction performance and the advantages of learning from local graph structure (+1.5 points in MRR for ConceptNet) when training on subgraphs for computational efficiency. Further analysis on model predictions shines light on the types of commonsense knowledge that language models capture well.
Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampling) operations, that play an important role in learning hierarchical representations, are usually overlooked. In this paper, we propose a novel graph pooling operator, called Hierarchical Graph Pooling with Structure Learning (HGP-SL), which can be integrated into various graph neural network architectures. HGP-SL incorporates graph pooling and structure learning into a unified module to generate hierarchical representations of graphs. More specifically, the graph pooling operation adaptively selects a subset of nodes to form an induced subgraph for the subsequent layers. To preserve the integrity of graph's topological information, we further introduce a structure learning mechanism to learn a refined graph structure for the pooled graph at each layer. By combining HGP-SL operator with graph neural networks, we perform graph level representation learning with focus on graph classification task. Experimental results on six widely used benchmarks demonstrate the effectiveness of our proposed model.
Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues and improve the performance of recommender systems. In this paper, we consider knowledge graphs as the source of side information. We propose MKR, a Multi-task feature learning approach for Knowledge graph enhanced Recommendation. MKR is a deep end-to-end framework that utilizes knowledge graph embedding task to assist recommendation task. The two tasks are associated by cross&compress units, which automatically share latent features and learn high-order interactions between items in recommender systems and entities in the knowledge graph. We prove that cross&compress units have sufficient capability of polynomial approximation, and show that MKR is a generalized framework over several representative methods of recommender systems and multi-task learning. Through extensive experiments on real-world datasets, we demonstrate that MKR achieves substantial gains in movie, book, music, and news recommendation, over state-of-the-art baselines. MKR is also shown to be able to maintain a decent performance even if user-item interactions are sparse.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191