arXiv subjects

Hongzhi Wang

Publications and source records attributed to Hongzhi Wang.

At least 73 records · Page 4Linked to original sources

arXiv2023

MaxCorrMGNN: A Multi-Graph Neural Network Framework for Generalized Multimodal Fusion of Medical Data for Outcome Prediction

With the emergence of multimodal electronic health records, the evidence for an outcome may be captured across multiple modalities ranging from clinical to imaging and genomic data. Predicting outcomes effectively requires fusion frameworks capable of modeling fine-grained and multi-faceted complex interactions between modality features within and across patients. We develop an innovative fusion approach called MaxCorr MGNN that models non-linear modality correlations within and across patients through Hirschfeld-Gebelein-Renyi maximal correlation (MaxCorr) embeddings, resulting in a multi-layered graph that preserves the identities of the modalities and patients. We then design, for the first time, a generalized multi-layered graph neural network (MGNN) for task-informed reasoning in multi-layered graphs, that learns the parameters defining patient-modality graph connectivity and message passing in an end-to-end fashion. We evaluate our model an outcome prediction task on a Tuberculosis (TB) dataset consistently outperforming several state-of-the-art neural, graph-based and traditional fusion techniques.

cs.LG↗

arXiv2023

One stone, two birds: A lightweight multidimensional learned index with cardinality support

Innovative learning based structures have recently been proposed to tackle index and cardinality estimation tasks, specifically learned indexes and data driven cardinality estimators. These structures exhibit excellent performance in capturing data distribution, making them promising for integration into AI driven database kernels. However, accurate estimation for corner case queries requires a large number of network parameters, resulting in higher computing resources on expensive GPUs and more storage overhead. Additionally, the separate implementation for CE and learned index result in a redundancy waste by storage of single table distribution twice. These present challenges for designing AI driven database kernels. As in real database scenarios, a compact kernel is necessary to process queries within a limited storage and time budget. Directly integrating these two AI approaches would result in a heavy and complex kernel due to a large number of network parameters and repeated storage of data distribution parameters. Our proposed CardIndex structure effectively killed two birds with one stone. It is a fast multidim learned index that also serves as a lightweight cardinality estimator with parameters scaled at the KB level. Due to its special structure and small parameter size, it can obtain both CDF and PDF information for tuples with an incredibly low latency of 1 to 10 microseconds. For tasks with low selectivity estimation, we did not increase the model's parameters to obtain fine grained point density. Instead, we fully utilized our structure's characteristics and proposed a hybrid estimation algorithm in providing fast and exact results.

cs.DB↗

arXiv2023

TodyNet: Temporal Dynamic Graph Neural Network for Multivariate Time Series Classification

Multivariate time series classification (MTSC) is an important data mining task, which can be effectively solved by popular deep learning technology. Unfortunately, the existing deep learning-based methods neglect the hidden dependencies in different dimensions and also rarely consider the unique dynamic features of time series, which lack sufficient feature extraction capability to obtain satisfactory classification accuracy. To address this problem, we propose a novel temporal dynamic graph neural network (TodyNet) that can extract hidden spatio-temporal dependencies without undefined graph structure. It enables information flow among isolated but implicit interdependent variables and captures the associations between different time slots by dynamic graph mechanism, which further improves the classification performance of the model. Meanwhile, the hierarchical representations of graphs cannot be learned due to the limitation of GNNs. Thus, we also design a temporal graph pooling layer to obtain a global graph-level representation for graph learning with learnable temporal parameters. The dynamic graph, graph information propagation, and temporal convolution are jointly learned in an end-to-end framework. The experiments on 26 UEA benchmark datasets illustrate that the proposed TodyNet outperforms existing deep learning-based methods in the MTSC tasks.

cs.LG↗

arXiv2023

TS-Cabinet: Hierarchical Storage for Cloud-Edge-End Time-series Database

Hierarchical data storage is crucial for cloud-edge-end time-series database. Efficient hierarchical storage will directly reduce the storage space of local databases at each side and improve the access hit rate of data. However, no effective hierarchical data management strategy for cloud-edge-end time-series database has been proposed. To solve this problem, this paper proposes TS-Cabinet, a hierarchical storage scheduler for cloud-edge-end time-series database based on workload forecasting. To the best of our knowledge, it is the first work for hierarchical storage of cloud-edge-end time-series database. By building a temperature model, we calculate the current temperature for the timeseries data, and use the workload forecasting model to predict the data's future temperature. Finally, we perform hierarchical storage according to the data migration policy. We validate it on a public dataset, and the experimental results show that our method can achieve about 94% hit rate for data access on the cloud side and edge side, which is 12% better than the existing methods. TS-Cabinet can help cloud-edge-end time-series database avoid the storage overhead caused by storing the full amount of data at all three sides, and greatly reduce the data transfer overhead between each side when collaborative query processing.

cs.DB↗

arXiv2022

TENSILE: A Tensor granularity dynamic GPU memory scheduling method toward multiple dynamic workloads system

Recently, deep learning has been an area of intense research. However, as a kind of computing-intensive task, deep learning highly relies on the scale of GPU memory, which is usually prohibitive and scarce. Although some extensive works have been proposed for dynamic GPU memory management, they are hard to apply to systems with multiple dynamic workloads, such as in-database machine learning systems. In this paper, we demonstrated TENSILE, a method of managing GPU memory in tensor granularity to reduce the GPU memory peak, considering the multiple dynamic workloads. TENSILE tackled the cold-starting and across-iteration scheduling problem existing in previous works. We implemented TENSILE on a deep learning framework built by ourselves and evaluated its performance. The experiment results show that TENSILE can save more GPU memory with less extra overhead than prior works in single and multiple dynamic workloads scenarios.

cs.DC↗

arXiv2022

Fusing Modalities by Multiplexed Graph Neural Networks for Outcome Prediction in Tuberculosis

In a complex disease such as tuberculosis, the evidence for the disease and its evolution may be present in multiple modalities such as clinical, genomic, or imaging data. Effective patient-tailored outcome prediction and therapeutic guidance will require fusing evidence from these modalities. Such multimodal fusion is difficult since the evidence for the disease may not be uniform across all modalities, not all modality features may be relevant, or not all modalities may be present for all patients. All these nuances make simple methods of early, late, or intermediate fusion of features inadequate for outcome prediction. In this paper, we present a novel fusion framework using multiplexed graphs and derive a new graph neural network for learning from such graphs. Specifically, the framework allows modalities to be represented through their targeted encodings, and models their relationship explicitly via multiplexed graphs derived from salient features in a combined latent space. We present results that show that our proposed method outperforms state-of-the-art methods of fusing modalities for multi-outcome prediction on a large Tuberculosis (TB) dataset.

cs.LG↗

arXiv2022

Differentiable Self-Adaptive Learning Rate

Learning rate adaptation is a popular topic in machine learning. Gradient Descent trains neural nerwork with a fixed learning rate. Learning rate adaptation is proposed to accelerate the training process through adjusting the step size in the training session. Famous works include Momentum, Adam and Hypergradient. Hypergradient is the most special one. Hypergradient achieved adaptation by calculating the derivative of learning rate with respect to cost function and utilizing gradient descent for learning rate. However, Hypergradient is still not perfect. In practice, Hypergradient fail to decrease training loss after learning rate adaptation with a large probability. Apart from that, evidence has been found that Hypergradient are not suitable for dealing with large datesets in the form of minibatch training. Most unfortunately, Hypergradient always fails to get a good accuracy on the validation dataset although it could reduce training loss to a very tiny value. To solve Hypergradient's problems, we propose a novel adaptation algorithm, where learning rate is parameter specific and internal structured. We conduct extensive experiments on multiple network models and datasets compared with various benchmark optimizers. It is shown that our algorithm can achieve faster and higher qualified convergence than those state-of-art optimizers.

cs.LG↗

arXiv2022

AAE: An Active Auto-Estimator for Improving Graph Storage

Nowadays, graph becomes an increasingly popular model in many real applications. The efficiency of graph storage is crucial for these applications. Generally speaking, the tune tasks of graph storage rely on the database administrators (DBAs) to find the best graph storage. However, DBAs make the tune decisions by mainly relying on their experiences and intuition. Due to the limitations of DBAs's experiences, the tunes may have an uncertain performance and conduct worse efficiency. In this paper, we observe that an estimator of graph workload has the potential to guarantee the performance of tune operations. Unfortunately, because of the complex characteristics of graph evaluation task, there exists no mature estimator for graph workload. We formulate the evaluation task of graph workload as a classification task and carefully design the feature engineering process, including graph data features, graph workload features and graph storage features. Considering the complex features of graph and the huge time consumption in graph workload execution, it is difficult for the graph workload estimator to obtain enough training set. So, we propose an active auto-estimator (AAE) for the graph workload evaluation by combining the active learning and deep learning. AAE could achieve good evaluation efficiency with limited training set. We test the time efficiency and evaluation accuracy of AAE with two open source graph data, LDBC and Freebase. Experimental results show that our estimator could efficiently complete the graph workload evaluation in milliseconds.

cs.DB↗

arXiv2022

EEML: Ensemble Embedded Meta-learning

To accelerate learning process with few samples, meta-learning resorts to prior knowledge from previous tasks. However, the inconsistent task distribution and heterogeneity is hard to be handled through a global sharing model initialization. In this paper, based on gradient-based meta-learning, we propose an ensemble embedded meta-learning algorithm (EEML) that explicitly utilizes multi-model-ensemble to organize prior knowledge into diverse specific experts. We rely on a task embedding cluster mechanism to deliver diverse tasks to matching experts in training process and instruct how experts collaborate in test phase. As a result, the multi experts can focus on their own area of expertise and cooperate in upcoming task to solve the task heterogeneity. The experimental results show that the proposed method outperforms recent state-of-the-arts easily in few-shot learning problem, which validates the importance of differentiation and cooperation.

cs.LG↗

arXiv2022

FIND:Explainable Framework for Meta-learning

Meta-learning is used to efficiently enable the automatic selection of machine learning models by combining data and prior knowledge. Since the traditional meta-learning technique lacks explainability, as well as shortcomings in terms of transparency and fairness, achieving explainability for meta-learning is crucial. This paper proposes FIND, an interpretable meta-learning framework that not only can explain the recommendation results of meta-learning algorithm selection, but also provide a more complete and accurate explanation of the recommendation algorithm's performance on specific datasets combined with business scenarios. The validity and correctness of this framework have been demonstrated by extensive experiments.

cs.LG↗

arXiv2022

AutoTS: Automatic Time Series Forecasting Model Design Based on Two-Stage Pruning

Automatic Time Series Forecasting (TSF) model design which aims to help users to efficiently design suitable forecasting model for the given time series data scenarios, is a novel research topic to be urgently solved. In this paper, we propose AutoTS algorithm trying to utilize the existing design skills and design efficient search methods to effectively solve this problem. In AutoTS, we extract effective design experience from the existing TSF works. We allow the effective combination of design experience from different sources, so as to create an effective search space containing a variety of TSF models to support different TSF tasks. Considering the huge search space, in AutoTS, we propose a two-stage pruning strategy to reduce the search difficulty and improve the search efficiency. In addition, in AutoTS, we introduce the knowledge graph to reveal associations between module options. We make full use of these relational information to learn higher-level features of each module option, so as to further improve the search quality. Extensive experimental results show that AutoTS is well-suited for the TSF area. It is more efficient than the existing neural architecture search algorithms, and can quickly design powerful TSF model better than the manually designed ones.

cs.LG↗

arXiv2022

Efficient Semi-External Depth-First Search

As the sizes of graphs grow rapidly, currently many real-world graphs can hardly be loaded in the main memory. It becomes a hot topic to compute depth-first search (DFS) results, i.e., depth-first order or DFS-Tree, on semi-external memory model. Semi-external algorithms assume the main memory could at least hold a spanning tree T of a graph G, and gradually restructure T into a DFS-Tree, which is non-trivial. In this paper, we present a comprehensive study of semi-external DFS problem. Based on our theoretical analysis of its main challenge, we introduce a new semi-external DFS algorithm, named EP-DFS, with a lightweight index N+-index. Unlike traditional algorithms, we focus on addressing such complex problem efficiently not only with less I/Os, but also with simpler CPU calculation (implementation-friendly) and less random I/O accesses (key-to-efficiency). Extensive experimental evaluation is conducted on both synthetic and real graphs. The experimental results confirm that our EP-DFS algorithm significantly outperforms existing algorithms.

cs.DB↗

arXiv2022

Dynamic Relation Repairing for Knowledge Enhancement

Dynamic relation repair aims to efficiently validate and repair the instances for knowledge graph enhancement (KGE), where KGE captures missing relations from unstructured data and leads to noisy facts to the knowledge graph. With the prosperity of unstructured data, an online approach is asked to clean the new RDF tuples before adding them to the knowledge base. To clean the noisy RDF tuples, graph constraint processing is a common but intractable approach. Plus, when adding new tuples to the knowledge graph, new graph patterns would be created, whereas the explicit discovery of graph constraints is also intractable. Therefore, although the dynamic relation repair has an unfortunate hardness, it is a necessary approach for enhancing knowledge graphs effectively under the fast-growing unstructured data. Motivated by this, we establish a dynamic repairing and enhancing structure to analyze its hardness on basic operations. To ensure dynamic repair and validation, we introduce implicit graph constraints, approximate graph matching, and linkage prediction based on localized graph patterns. To validate and repair the RDF tuples efficiently, we further study the cold start problems for graph constraint processing. Experimental results on real datasets demonstrate that our proposed approach can capture and repair instances with wrong relation labels dynamically and effectively.

cs.DB↗

arXiv2022

AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategy

Model compression methods can reduce model complexity on the premise of maintaining acceptable performance, and thus promote the application of deep neural networks under resource constrained environments. Despite their great success, the selection of suitable compression methods and design of details of the compression scheme are difficult, requiring lots of domain knowledge as support, which is not friendly to non-expert users. To make more users easily access to the model compression scheme that best meet their needs, in this paper, we propose AutoMC, an effective automatic tool for model compression. AutoMC builds the domain knowledge on model compression to deeply understand the characteristics and advantages of each compression method under different settings. In addition, it presents a progressive search strategy to efficiently explore pareto optimal compression scheme according to the learned prior knowledge combined with the historical evaluation information. Extensive experimental results show that AutoMC can provide satisfying compression schemes within short time, demonstrating the effectiveness of AutoMC.

cs.LG↗

arXiv2022

TPAD: Identifying Effective Trajectory Predictions Under the Guidance of Trajectory Anomaly Detection Model

Trajectory Prediction (TP) is an important research topic in computer vision and robotics fields. Recently, many stochastic TP models have been proposed to deal with this problem and have achieved better performance than the traditional models with deterministic trajectory outputs. However, these stochastic models can generate a number of future trajectories with different qualities. They are lack of self-evaluation ability, that is, to examine the rationality of their prediction results, thus failing to guide users to identify high-quality ones from their candidate results. This hinders them from playing their best in real applications. In this paper, we make up for this defect and propose TPAD, a novel TP evaluation method based on the trajectory Anomaly Detection (AD) technique. In TPAD, we firstly combine the Automated Machine Learning (AutoML) technique and the experience in the AD and TP field to automatically design an effective trajectory AD model. Then, we utilize the learned trajectory AD model to examine the rationality of the predicted trajectories, and screen out good TP results for users. Extensive experimental results demonstrate that TPAD can effectively identify near-optimal prediction results, improving stochastic TP models' practical application effect.

cs.LG↗

arXiv2021

Addressing Deep Learning Model Uncertainty in Long-Range Climate Forecasting with Late Fusion

Global warming leads to the increase in frequency and intensity of climate extremes that cause tremendous loss of lives and property. Accurate long-range climate prediction allows more time for preparation and disaster risk management for such extreme events. Although machine learning approaches have shown promising results in long-range climate forecasting, the associated model uncertainties may reduce their reliability. To address this issue, we propose a late fusion approach that systematically combines the predictions from multiple models to reduce the expected errors of the fused results. We also propose a network architecture with the novel denormalization layer to gain the benefits of data normalization without actually normalizing the data. The experimental results on long-range 2m temperature forecasting show that the framework outperforms the 30-year climate normals, and the accuracy can be improved by increasing the number of models.

cs.LG↗

arXiv2021

Experience-Enhanced Learning: One Size Still does not Fit All in Automatic Database

Recent years, the database committee has attempted to develop automatic database management systems. Although some researches show that the applying AI to data management is a significant and promising direction, there still exists many problems in implementing these techniques to real applications (long training time, various environments and unstable performance). In this paper, we discover that traditional rule based methods have the potential to solve the above problems. We propose three methodologies for improving learned methods, i.e. label collection for efficiently pre-training, knowledge base for model transfer and theoretical guarantee for stable performance. We implement our methodologies on two widely used learning approaches, deep learning and reinforcement learning. Firstly, the novel experience enhanced deep learning (EEDL) could achieve efficient training and stable performance. We evaluate EEDL with cardinality estimation, an essential database management. The experimental results on four real dataset [1] show that our EEDL could outperforms the general DL model [2]. Secondly, we design a novel experience-enhanced reinforcement learning (EERL), which could efficiently converge and has better performance than general RL models [3]. We test EERL with online index tuning task. The experiments on TPC-H shows that EERL could accelerate the convergence of agent and generate better solution that generalizes the reinforcement learning.

cs.DB↗

arXiv2021

Search For Deep Graph Neural Networks

Current GNN-oriented NAS methods focus on the search for different layer aggregate components with shallow and simple architectures, which are limited by the 'over-smooth' problem. To further explore the benefits from structural diversity and depth of GNN architectures, we propose a GNN generation pipeline with a novel two-stage search space, which aims at automatically generating high-performance while transferable deep GNN models in a block-wise manner. Meanwhile, to alleviate the 'over-smooth' problem, we incorporate multiple flexible residual connection in our search space and apply identity mapping in the basic GNN layers. For the search algorithm, we use deep-q-learning with epsilon-greedy exploration strategy and reward reshaping. Extensive experiments on real-world datasets show that our generated GNN models outperforms existing manually designed and NAS-based ones.

cs.LG↗