Wenchao Yul NEC Labs AmericaWenchao Yu is a Senior Researcher in the Data Science and System Security Department at NEC Laboratories America in Princeton, NJ. He earned his Ph.D. in Computer Science from the University of California, Los Angeles (UCLA).

His research focuses on multimodal time-series analysis, explainable AI, and agentic AI systems that integrate large language models with temporal and multimodal data. By developing interpretable and scalable methods, Yu aims to create AI agents that can reason over complex time-series signals and deliver actionable insights in domains such as finance, healthcare, and intelligent infrastructure. See more about Wenchao on Google Scholar.

Posts

Learning to Drop: Robust Graph Neural Network via Topological Denoising

/in /by

Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics. The key idea is to recursively propagate and aggregate information along the edges of the given graph. Despite their success, however, the existing GNNs are usually sensitive to the quality of the input graph. Real-world graphs are often noisy and contain task-irrelevant edges, which may lead to suboptimal generalization performance in the learned GNN models. In this paper, we propose PTDNet, a parameterized topological denoising network, to improve the robustness and generalization performance of GNNs by learning to drop task-irrelevant edges. PTDNet prunes task-irrelevant edges by penalizing the number of edges in the sparsified graph with parameterized networks. To take into consideration the topology of the entire graph, the nuclear norm regularization is applied to impose the low-rank constraint on the resulting sparsified graph for better generalization. PTDNet can be used as a key component in GNN models to improve their performances on various tasks, such as node classification and link prediction. Experimental studies on both synthetic and benchmark datasets show that PTDNet can improve the performance of GNNs significantly and the performance gain becomes larger for more noisy datasets.

Read more

Multi-Task Recurrent Modular Networks

/in /by

We consider the models of deep multi-task learning with recurrent architectures that exploit regularities across tasks to improve the performance of multiple sequence processing tasks jointly. Most existing architectures are painstakingly customized to learn task relationships for different problems, which is not flexible enough to model the dynamic task relationships and lacks generalization abilities to novel test-time scenarios. We propose multi-task recurrent modular networks (MT-RMN) that can be incorporated in any multi-task recurrent models to address the above drawbacks. MT-RMN consists of a shared encoder and multiple task-specific decoders, and recurrently operates over time. For better flexibility, it modularizes the encoder into multiple layers of sub-networks and dynamically controls the connection between these sub-networks and the decoders at different time steps, which provides the recurrent networks with varying degrees of parameter sharing for tasks with dynamic relatedness. For the generalization ability, MT-RMN aims to discover a set of generalizable sub-networks in the encoder that are assembled in different ways for different tasks. The policy networks augmented with the differentiable routers are utilized to make the binary connection decisions between the sub-networks. The experimental results on three multi-task sequence processing datasets consistently demonstrate the effectiveness of MT-RMN.

Read more

Parameterized Explainer for Graph Neural Network

/in /by

Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging open problem. The leading method independently addresses the local explanations (i.e., important subgraph structure and node features) to interpret why a GNN model makes the prediction for a single instance, e.g. a node or a graph. As a result, the explanation generated is painstakingly customized for each instance. The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to the lack of generalizability and hindering it from being used in the inductive setting. Besides, as it is designed for explaining a single instance, it is challenging to explain a set of instances naturally (e.g., graphs of a given class). In this study, we address these key challenges and propose PGExplainer, a parameterized explainer for GNNs. PGExplainer adopts a deep neural network to parameterize the generation process of explanations, which enables PGExplainer a natural approach to explaining multiple instances collectively. Compared to the existing work, PGExplainer has better generalization ability and can be utilized in an inductive setting easily. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24.7% relative improvement in AUC on explaining graph classification over the leading baseline.

Read more

Node Classification in Temporal Graphs through Stochastic Sparsification and Temporal Structural Convolution

/in /by

Node classification in temporal graphs aims to predict node labels based on historical observations. In real-world applications, temporal graphs are complex with both graph topology and node attributes evolving rapidly, which poses a high overfitting risk to existing graph learning approaches. In this paper, we propose a novel Temporal Structural Network (TSNet) model, which jointly learns temporal and structural features for node classification from the sparsified temporal graphs. We show that the proposed TSNet learns how to sparsify temporal graphs to favor the subsequent classification tasks and prevent overfitting from complex neighborhood structures. The effective local features are then extracted by simultaneous convolutions in temporal and spatial domains. Using the standard stochastic gradient descent and backpropagation techniques, TSNet iteratively optimizes sparsification and node representations for subsequent classification tasks. Experimental study on public benchmark datasets demonstrates the competitive performance of the proposed model in node classification. Besides, TSNet has the potential to help domain experts to interpret and visualize the learned models.

Read more

Robust Graph Representation Learning via Neural Sparsification

/in /by

Graph representation learning serves as the core of important prediction tasks, ranging from product recommendation to fraud detection. Reallife graphs usually have complex information in the local neighborhood, where each node is described by a rich set of features and connects to dozens or even hundreds of neighbors. Despite the success of neighborhood aggregation in graph neural networks, task-irrelevant information is mixed into nodes’ neighborhood, making learned models suffer from sub-optimal generalization performance. In this paper, we present NeuralSparse, a supervised graph sparsification technique that improves generalization power by learning to remove potentially task-irrelevant edges from input graphs. Our method takes both structural and nonstructural information as input, utilizes deep neural networks to parameterize sparsification processes, and optimizes the parameters by feedback signals from downstream tasks. Under the NeuralSparse framework, supervised graph sparsification could seamlessly connect with existing graph neural networks for more robust performance. Experimental results on both benchmark and private datasets show that NeuralSparse can yield up to 7.2% improvement in testing accuracy when working with existing graph neural networks on node classification tasks.

Read more

Inductive and Unsupervised Representation Learning on Graph Structured Objects

/in /by

Inductive and unsupervised graph learning is a critical technique for predictive or information retrieval tasks where label information is difficult to obtain. It is also challenging to make graph learning inductive and unsupervised at the same time, as learning processes guided by reconstruction error based loss functions inevitably demand graph similarity evaluation that is usually computationally intractable. In this paper, we propose a general framework SEED (Sampling, Encoding, and Embedding Distributions) for inductive and unsupervised representation learning on graph structured objects. Instead of directly dealing with the computational challenges raised by graph similarity evaluation, given an input graph, the SEED framework samples a number of subgraphs whose reconstruction errors could be efficiently evaluated, encodes the subgraph samples into a collection of subgraph vectors, and employs the embedding of the subgraph vector distribution as the output vector representation for the input graph. By theoretical analysis, we demonstrate the close connection between SEED and graph isomorphism. Using public benchmark datasets, our empirical study suggests the proposed SEED framework is able to achieve up to 10% improvement, compared with competitive baseline methods.

Read more

Adversarial Cooperative Imitation Learning for Dynamic Treatment Regimes

/in /by

Recent developments in discovering dynamic treatment regimes (DTRs) have heightened the importance of deep reinforcement learning (DRL) which are used to recover the doctor’s treatment policies. However, existing DRL-based methods expose the following limitations: 1) supervised methods based on behavior cloning suffer from compounding errors, 2) the self-defined reward signals in reinforcement learning models are either too sparse or need clinical guidance, 3) only positive trajectories (e.g. survived patients) are considered in current imitation learning models, with negative trajectories (e.g. deceased patients) been largely ignored, which are examples of what not to do and could help the learned policy avoid repeating mistakes. To address these limitations, in this paper, we propose the adversarial cooperative imitation learning model, ACIL, to deduce the optimal dynamic treatment regimes that mimics the positive trajectories while differs from the negative trajectories. Specifically, two discriminators are used to help achieve this goal: an adversarial discriminator is designed to minimize the discrepancies between the trajectories generated from the policy and the positive trajectories, and a cooperative discriminator is used to distinguish the negative trajectories from the positive and generated trajectories. The reward signals from the discriminators are utilized to refine the policy for dynamic treatment regimes. Experiments on the publicly real-world medical data demonstrate that ACIL improves the likelihood of patient survival and provides better dynamic treatment regimes with the exploitation of information from both positive and negative trajectories.

Read more

Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time Series

/in /by

The problem of learning and forecasting underlying trends in time series data arises in a variety of applications, such as traffic management, energy optimization, etc. In literature, a trend in time series is characterized by the slope and duration, and its prediction is then to forecast the two values of the subsequent trend given historical data of the time series. For this problem, existing approaches mainly deal with the case in univariate time series. However, in many real-world applications, there are multiple variables at play, and handling all of them at the same time is crucial for an accurate prediction. A natural way is to employ multi-task learning (MTL) techniques in which the trend learning of each time series is treated as a task. The key point of MTL is to learn task relatedness to achieve better parameter sharing, which however is challenging in trend prediction task. First, effectively modeling the complex temporal patterns in different tasks is hard as the temporal and spatial dimensions are entangled. Second, the relatedness among tasks may change over time. In this paper, we propose a neural network, DeepTrends, for multivariate time series trend prediction. The core module of DeepTrends is a tensorized LSTM with adaptive shared memory (TLASM). TLASM employs the tensorized LSTM to model the temporal patterns of long-term trend sequences in an MTL setting. With an adaptive shared memory, TLASM is able to learn the relatedness among tasks adaptively, based upon which it can dynamically vary degrees of parameter sharing among tasks. To further consider short-term patterns, DeepTrends utilizes a multi-task 1dCNN to learn the local time series features, and employs a task-specific sub-network to learn a mixture of long-term and short-term patterns for trend prediction. Extensive experiments on real datasets demonstrate the effectiveness of the proposed model.

Read more

Self-Attentive Attributed Network Embedding Through Adversarial Learning

/in /by

Network embedding aims to learn the low-dimensional representations/embeddings of vertices which preserve the structure and inherent properties of the networks. The resultant embeddings are beneficial to downstream tasks such as vertex classification and link prediction. A vast majority of real-world networks are coupled with a rich set of vertex attributes, which could be potentially complementary in learning better embeddings. Existing attributed network embedding models, with shallow or deep architectures, typically seek to match the representations in topology space and attribute space for each individual vertex by assuming that the samples from the two spaces are drawn uniformly. The assumption, however, can hardly be guaranteed in practice. Due to the intrinsic sparsity of sampled vertex sequences and incompleteness in vertex attributes, the discrepancy between the attribute space and the network topology space inevitably exists. Furthermore, the interactions among vertex attributes, a.k.a cross features, have been largely ignored by existing approaches. To address the above issues, in this paper, we propose Nettention, a self-attentive network embedding approach that can efficiently learn vertex embeddings on attributed network. Instead of sample-wise optimization, Nettention aggregates the two types of information through minimizing the difference between the representation distributions in the low-dimensional topology and attribute spaces. The joint inference is encapsulated in a generative adversarial training process, yielding better generalization performance and robustness. The learned distributions consider both locality-preserving and global reconstruction constraints which can be inferred from the learning of the adversarially regularized autoencoders. Additionally, a multi-head self-attention module is developed to explicitly model the attribute interactions. Extensive experiments on benchmark datasets have verified the effectiveness of the proposed Nettention model on a variety of tasks, including vertex classification and link prediction.

Read more

Learning Robust Representations with Graph Denoising Policy Network

/in /by

Existing representation learning methods based on graph neural networks and their variants rely on the aggregation of neighborhood information, which makes it sensitive to noises in the graph, e.g. erroneous links between nodes, incorrect/missing node features. In this paper, we propose Graph Denoising Policy Network (short for GDPNet) to learn robust representations from noisy graph data through reinforcement learning. GDPNet first selects signal neighborhoods for each node, and then aggregates the information from the selected neighborhoods to learn node representations for the down-stream tasks. Specifically, in the signal neighborhood selection phase, GDPNet optimizes the neighborhood for each target node by formulating the process of removing noisy neighborhoods as a Markov decision process and learning a policy with task-specific rewards received from the representation learning phase. In the representation learning phase, GDPNet aggregates features from signal neighbors to generate node representations for down-stream tasks, and provides task-specific rewards to the signal neighbor selection phase. These two phases are jointly trained to select optimal sets of neighbors for target nodes with maximum cumulative task-specific rewards, and to learn robust representations for nodes. Experimental results on node classification task demonstrate the effectiveness of GDNet, outperforming the state-of-the-art graph representation learning methods on several well-studied datasets.

Read more