PROJECTS
PEOPLE
PUBLICATIONS
PATENTS
Data Science and System Security
Wei Cheng is a Principal Researcher in the Data Science & System Security Department at NEC Labs America. He received his Ph.D. from the Department of Computer Science at the University of North Carolina at Chapel Hill, in 2015, advised by Prof. Wei Wang. His research interests include data science, machine learning, and bioinformatics.
He has filed over sixty patents and published more than ninety research papers in top-tier conferences such as NeurIPS, ICML, SIGKDD, ICLR, WWW, EMNLP, ISMB, and journals such as Nature, Science, TNNLS, TKDE, Bioinformatics, etc. His research results received Best Research Paper Runner-Up Award at SIGKDD 2016 and were nominated for the Best Paper Award at ICDM 2018, ICDM 2017, ICDM 2015, and SDM 2012. He received the “NEC Business Contribution Award” in 2021 and 2022, respectively. His research has been cited more than 13,000 times. He has also served as area chair and senior program committee member for several top-tier conferences, including SIGKDD, IJCAI, SDM, AAAI, WSDM, etc.
Overview: Unstructured data is growing at an unprecedented rate, valuable knowledge, including findings, observations, business demand, opportunities, is widely recorded as texts in documents. We are developing advanced analysis engines for mining text data in documents, aiming to discover valuable knowledge from large-scale documents and provide informed decision-making for users.
Overview: In many big data applications, data with complex structures are connected for their explicit/implicit interactions and are naturally represented as graphs/networks. The world is full of complex and dynamic interactions between diverse objects. The flood of dynamic graph data poses great computational challenges and entails interdisciplinary collaborations.
Overview: By leveraging big data and deep learning, in recent years, AI technologies have made significant progress. They have been adopted in many applications, including malware detection, image classification, and stock market prediction. As our society becomes more automated, more and more systems will rely on AI techniques. And instead of augmenting human decisions, some AI systems will make their own decisions and execute autonomously.
As large language models increasingly serve as autonomous coding agents, code documentation must be optimized for agent comprehension rather than human readability. We frame agent-oriented documentation generation as a black-box optimization problem over the documentation space, where quality is measured
Chain-of-Thought (CoT) reasoning has driven recent gains of large language models (LLMs) on reasoning-intensive tasks by externalizing intermediate steps. However, excessive or redundant reasoning so-called overthinking can increase inference costs and lead LLMs toward incorrect conclusions. In
Automatically solving optimization problems from natural language descriptions with both efficiency and reliability is highly desirable but remains challenging. Language model hallucinations and the limited availability of labeled datasets often result in misaligned formulations, code errors, and feasibility
NEC Laboratories America researchers are heading to Seoul this July for ICML 2026, the Forty-Third International Conference on Machine Learning. One of the most prestigious gatherings in the field, ICML draws academic and industry researchers from around the world to share work spanning machine learning,
NEC Laboratories America heads to ACL 2026 in San Diego, California, July 2–7, to present accepted papers spanning knowledge updating and memory control in large language models, task-aware cultural alignment, uncertainty-aware reasoning, and adaptive chain-of-thought optimization, representing some
Most retrieval-augmented generation systems stop at documents, ignoring the relational databases that power finance, healthcare, and research. Our researchers built a rule-driven framework that learns which source to query for each question, delivering better answers at lower computational cost.
Large Language Models (LLMs) have shown remarkable performance on general Question Answering (QA), yet they often struggle in domain-specific scenarios where accurate and up-to-date information is required. Retrieval-Augmented Generation (RAG) addresses this limitation by enriching LLMs with external
Large Language Models (LLMs) excel at many reasoning tasks but struggle with knowledge-intensive queries due to their inability to dynamically access up-to-date or domain-specific information. Retrieval-Augmented Generation (RAG) has emerged as a promising solution, enabling LLMs to ground their responses
Automatically extracting workflows as procedural graphs from natural language is promising yet underexplored, demanding both structural validity and logical alignment. While recent large language models (LLMs) show potential for procedural graph extraction, they often produce ill-formed structures or
The rapid advancement of large language models (LLMs) such as ChatGPT, DeepSeek, and Claude has significantly increased the presence of AI-generated text in digital communication. This trend has heightened the need for reliable detection methods to distinguish between human-authored and machine-generated
Time series, typically represented as numerical sequences, can also be transformed into images and texts, offering multi-modal views (MMVs) of the same underlying signal. These MMVs can reveal complementary patterns and enable the use of powerful pre-trained large models, such as large vision models
Large Language Models (LLMs) offer promising capabilities for tackling complex reasoning tasks, including optimization problems. However, existing methods either rely on prompt engineering, which leads to poor generalization across problem types, or require costly supervised training. We introduce SolverLLM,
Time series analysis provides essential insights for real-world system dynamics and informs downstream decision-making, yet most existing methods often overlook the rich contextual signals present in auxiliary modalities. To bridge this gap, we introduce TimeXL, a multi-modal prediction framework that
Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually designed based on domain knowledge. We propose dynamic decomposition,
NEC Laboratories America is heading to San Diego for NeurIPS 2025, where our researchers will present cutting-edge work spanning optimization, AI systems, language modeling, and trustworthy machine learning. multi-agent coordination, scalable training, efficient inference, and techniques for detecting
Extreme events frequently occur in real-world time series and often carry significant practical implications. In domains such as climate and healthcare, these events, such as floods, heatwaves, or acute medical episodes, can lead to serious consequences. Accurate forecasting of such events is therefore
Large language models (LLMs) have significantly advanced the field of natural language processing (NLP), providing a highly useful, task-agnostic foundation for a wide range of applications. However, directly applying LLMs to solve sophisticated problems in specific domains meets many hurdles, caused
Time series analysis has witnessed the inspiring development from traditional autoregressive models, deep learning models, to recent Transformers and Large Language Models (LLMs). Efforts in leveraging vision models for time series analysis have also been made along the way but are less visible to the
Large language models (LLMs) integrated into multi-step agent systems enable complex decision-making processes across various applications. However, their outputs often lack reliability, making uncertainty estimation crucial. Existing uncertainty estimation methods primarily focus on final-step outputs,
The recent proliferation of photorealistic images created by generative models has sparked both excitement and concern, as these images are increasingly indistinguishable from real ones to the human eye. While offering new creative and commercial possibilities, the potential for misuse, such as in misinformation
Prompt tuning is highly effective in efficiently extracting knowledge from foundation models, encompassing both language, vision, and vision-language models. However, the efficacy of employing fixed soft prompts with a predetermined position for concatenation with inputs for all instances, irrespective
Large Language Models (LLMs) exhibit potential artificial generic intelligence recently, however, their usage is costly with high response latency. Given mixed LLMs with their own strengths and weaknesses, LLM routing aims to identify the most suitable model for each query in the stream to maximize response
Inference scaling methods often rely on decomposing problems into steps, followed by sampling and selecting the best next steps. However, these steps and their sizes are typically fixed or depend on domain knowledge. We propose dynamic decomposition, a method that adaptively and automatically breaks
Inference scaling methods often rely on decomposing problems into steps, followed by sampling and selecting the best next steps. However, these steps and their sizes are typically fixed or depend on domain knowledge. We propose dynamic decomposition, a method that adaptively and automatically breaks
Recent research has developed a number of eXplainable AI (XAI) techniques, such as gradient-based approaches, input perturbation-base methods, and black-box explanation methods. While these XAI techniques can extract meaningful insights from deep learning models, how to properly evaluate them remains
The advent of large language models (LLMs) has revolutionized the field of text generation, producing outputs that closely mimic human-like writing. Although academic and industrial institutions have developed detectors to prevent the malicious usage of LLM-generated texts, other research has doubt about
We frame code generation as a black-box optimization problem within the code space and demonstrate how optimization-inspired techniques can enhance inference scaling. Based on this perspective, we propose SCATTERED FOREST SEARCH (SFS), a novel approach that improves solution diversity and better exploits
Visual Language Models (VLMs) like GPT-4V have broadened the scope of LLM applications, yet they face significant challenges in accurately processing visual details, particularly in scientific diagrams. This paper explores the necessity of meticulous visual detail collection and region decomposition
NEC Laboratories America (NECLA) is advancing the frontier of Graph Neural Networks (GNNs), a transformative AI technology that processes complex, interconnected data. Through innovations like PTDNet for robust learning, novel frameworks for explainability, StrGNN for anomaly detection in dynamic graphs,
Time series data is essential in various applications, including climate modeling, healthcare monitoring, and financial analytics. Understanding the contextual information associated with real-world time series data is often essential for accurate and reliable event predictions. In this paper, we introduce
The advent of Large Language Models (LLMs) has revolutionized text generation, producing outputs that closely mimic human writing. This blurring of lines between machine- and human-written text presents new challenges in distinguishing one from the other a task further complicated by the frequent
The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content. Despite efforts to ethically align LLMs, these are often fragile and can be circumvented by jailbreaking attacks through optimized or manual adversarial
The burgeoning capabilities of advanced large language models (LLMs) such as ChatGPT have led to an increase in synthetic content generation with implications across a variety of sectors, including media, cybersecurity, public discourse, and education. As such, the ability to detect LLMs-generated content
Large Language Models (LLMs) have achieved exceptional capabilities in open generation across various domains, yet they encounter difficulties with tasks that require intensive knowledge. To address these challenges, methods for integrating knowledge have been developed, which augment LLMs with domain-specific
The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless, such domain-specific fine-tuning data often contains contextually sensitive personally identifiable information (PII).
Though Large Language Models (LLMs) have shown remarkable open-generation capabilities across diverse domains, they struggle with knowledge-intensive tasks. To alleviate this issue, knowledge integration methods have been proposed to enhance LLMs with domain-specific knowledge graphs using external modules.
In the context of long-tail classification on graphs, the vast majority of existing work primarily revolves around the development of model debiasing strategies, intending to mitigate class imbalances and enhance the overall performance. Despite the notable success, there is very limited literature that
Time series domain adaptation stands as a pivotal and intricate challenge with diverse applications, including but not limited to human activity recognition, sleep stage classification, and machine fault diagnosis. Despite the numerous domain adaptation techniques proposed to tackle this complex problem,
This paper introduces the retrieval-augmented large language model with Definite Finite Automaton (DFA-RAG), a novel framework designed to enhance the capabilities of conversational agents using large language models (LLMs). Traditional LLMs face challenges in generating regulated and compliant responses
Neural language models for commonsense reasoning often formulate the problem as a QA task and make predictions based on learned representations of language after fine-tuning. However, without providing any fine-tuning data and pre-defined answer candidates, can neural language models still answer commonsense
Large Language Models (LLMs) have exhibited remarkable proficiency across a wide array of NLP tasks. However, the escalation in model size also engenders substantial deployment costs. While few efforts have explored model pruning techniques to reduce the size of LLMs, they mainly center on general or
In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) and revolutionized various fields by providing a few task-relevant demonstrations in the prompt. However, trustworthy issues with LLMs response, such as hallucination, have also been actively discussed. Existing
Large language models (LLMs) have notably enhanced the fluency and diversity of machine-generated text. However, this progress also presents a significant challenge in detecting the origin of a given text, and current research on detection methods lags behind the rapid evolution of LLMs. Conventional
Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text, typically in the form of (subject, relation, object) triples. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods
Modern techniques like contrastive learning have been effectively used in many areas, including computer vision, natural language processing, and graph-structured data. Creating positive examples that assist the model in learning robust and discriminative representations is a crucial stage in contrastive
Graph Neural Networks (GNNs) are neural models that leverage the dependency structure in graphical data via message passing among the graph nodes. GNNs have emerged as pivotal architectures in analyzing graph-structured data, and their expansive application in sensitive domains requires a comprehensive
Imitation learning, which learns agent policy by mimicking expert demonstration, has shown promising results in many applications such as medical treatment regimes and self-driving vehicles. However, it remains a difficult task to interpret control policies learned by the agent. Difficulties mainly come
Time series domain adaptation stands as a pivotal and intricate challenge with diverse applications, including but not limited to human activity recognition, sleep stage classification, and machine fault diagnosis. Despite the numerous domain adaptation techniques proposed to tackle this complex problem,
Meta-learning enables quick adaptation of machine learning models to new tasks with limited data. While tasks could come from varying distributions in reality, most of the existing meta-learning methods consider both training and testing tasks as from the same uni-component distribution, overlooking
Open-ended Commonsense Reasoning is defined as solving a commonsense question without providing 1) a short list of answer candidates and 2) a pre-defined answer scope. Conventional ways of formulating the commonsense question into a question-answering form or utilizing external knowledge to learn retrieval-based
NEC Labs America is proud to be a Silver Sponsor for NeurIPS 2023 in New Orleans from December 10-16. Visit our booth to meet our team and learn about our intern opportunities in machine learning, data science, media analytics and integrated systems. Also, our Vijay Kumar.B.G, Samuel Schulter & Manmohan
Logs play a crucial role in system monitoring and debugging by recording valuable system information, including events and status. Although various methods have been proposed to detect anomalies in log sequences, they often overlook the significance of considering relationships among system components,
Read AutoTCL: Automated Time Series Contrastive Learning with Adaptive Augmentations publication. Modern techniques like contrastive learning have been effectively used in many areas, including computer vision, natural language processing, and graph-structured data. Creating positive examples that assist
Read FedSkill: Privacy Preserved Interpretable Skill Learning via Imitation publication. Imitation learning that replicates experts’ skills via their demonstrations has shown significant success in various decision-making tasks. However, two critical challenges still hinder the deployment of imitation
Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations. However, existing algorithms typically require a large number of high-quality demonstrations that are difficult and expensive to collect.
The recent trend towards Personalized Federated Learning (PFL) has garnered significant attention as it allows for the training of models that are tailored to each client while maintaining data privacy. However, current PFL techniques primarily focus on modeling the conditional distribution heterogeneity
Unsupervised anomaly detection approaches have been widely accepted in applications for industrial systems. Industrial systems often operate with multiple modes since they work for multiple purposes or under different conditions. In order to deal with the difficulty of anomaly detection due to multiple
Large language models (LLMs) have significantly advanced the field of natural language processing (NLP), providing a highly useful, task agnostic foundation for a wide range of applications. The great promise of LLMs as general task solvers motivated people to extend their functionality largely beyond
Imitation learning that mimics experts’ skills from their demonstrations has shown great success in discovering dynamic treatment regimes, i.e., the optimal decision rules to treat an individual patient based on related evolving treatment and covariate history. Existing imitation learning methods,
It has been demonstrated that prompt tuning is highly effective in efficiently eliciting knowledge from language models (LMs). However, the prompt tuning still lags behind fine tuning, especially when the LMs are small. P tuning v2 (Liu et al., 2021b) makes it comparable with finetuning by adding continuous
Text summarization has been a crucial problem in natural language processing (NLP) for several decades. It aims to condense lengthy documents into shorter versions while retaining the most critical information. Various methods have been proposed for text summarization, including extractive and abstractive
Various contrastive learning approaches have been proposed in recent years and have achieved significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key component of contrastive learning is to select appropriate augmentations,
Although many anomaly detection approaches have been developed for multivariate time series data, limited effort has been made in federated settings in which multivariate time series data are heterogeneously distributed among different edge devices while data sharing is prohibited. In this paper, we
Personalized Federated Learning (PFL) which collaboratively trains a federated model while considering local clients under privacy constraints has attracted much attention. Despite its popularity, it has been observed that existing PFL approaches result in sub-optimal solutions when the joint distribution
It is critical and important to detect anomalies in event sequences, which becomes widely available in many application domains. Indeed, various efforts have been made to capture abnormal patterns from event sequences through sequential pattern analysis or event representation learning. However, existing
Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes. However, most of the existing methods focus on the offline sound event detection, which suffers from the over-confidence issue of early-stage event detection and usually yield unreliable
Learning fine-grained embeddings is essential for extending the generalizability of models pre-trained on “coarse” labels (e.g., animals). It is crucial to fields for which fine-grained labeling (e.g., breeds of animals) is expensive, but fine-grained prediction is desirable, such as medicine. The dilemma
We target the task of cross-lingual Machine Reading Comprehension (MRC) in the direct zero-shot setting, by incorporating syntactic features from Universal Dependencies (UD), and the key features we use are the syntactic relations within each sentence. While previous work has demonstrated effective syntax-guided
Using deep reinforcement learning (DRL) to recover expert policies via imitation has been found to be promising in a wide range of applications. However, it remains a difficult task to interpret the control policy learned by the agent. Difficulties mainly come from two aspects: 1) agents in DRL are usually
InfoGCL: Information-Aware Graph Contrastive Learning Various graph contrastive learning models have been proposed to improve the performance of tasks on graph datasets in recent years. While effective and prevalent, these models are usually carefully customized. In particular, despite all recent work
Point-of-interest (POI) recommendation is an emerging area of research on location-based social networks to analyze user behaviors and contextual check-in information. For this problem, existing approaches, with shallow or deep architectures, have two major drawbacks. First, for these approaches, the
Compliments and concerns in reviews are valuable for understanding users’ shopping interests and their opinions with respect to specific aspects of certain items. Existing review-based recommenders favor large and complex language encoders that can only learn latent and uninterpretable text representations.
In many high-stakes applications of machine learning models, outputting only predictions or providing statistical confidence is usually insufficient to gain trust from end users, who often prefer a transparent reasoning paradigm. Despite the recent encouraging developments on deep networks for sequential
Imitation learning has been proved to be effective in mimicking experts’ behaviors from their demonstrations without access to explicit reward signals. Meanwhile, complex tasks, e.g., dynamic treatment regimes for patients with comorbidities, often suggest significant variability in expert demonstrations
Measuring document similarity plays an important role in natural language processing tasks. Most existing document similarity approaches suffer from the information gap caused by context and vocabulary mismatches when comparing varying-length texts. In this paper, we propose an unsupervised concept representation
Prognostics or early detection of incipient faults by leveraging the monitoring time series data in complex systems is valuable to automatic system management and predictive maintenance. However, this task is challenging. First, learning the multi-dimensional heterogeneous time series data with various
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
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,
Forecasting on Sparse Multivariate Time Series Forecasting on sparse multivariate time series (MTS) aims to model the predictors of future values of time series given their incomplete past, which is important for many emerging applications. However, most existing methods process MTS’s individually,
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
Accurate air turbulence forecasting can help airlines avoid hazardous turbulence, guide the routes that keep passengers safe, maximize efficiency, and reduce costs. Traditional turbulence forecasting approaches heavily rely on painstakingly customized turbulence indexes, which are less effective in dynamic
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
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
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
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
To subvert recent advances in perimeter and host security, the attacker community has developed and employed various attack vectors to make malware much more stealthy than before to penetrate the target system and prolong its presence. The advanced malware, or stealthy malware, impersonates or abuses
Recently, recommender systems have been able to emit substantially improved recommendations by leveraging user-provided reviews. Existing methods typically merge all reviews of a given user (item) into a long document, and then process user and item documents in the same manner. In practice, however,
Multivariate time series data are becoming increasingly ubiquitous in varies real-world applications such as smart city, power plant monitoring, wearable devices, etc. Given the current time series segment, how to retrieve similar segments within the historical data in an efficient and effective manner
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
Click-through rate (CTR) prediction is a critical task in online advertising and marketing. For this problem, existing approaches, with shallow or deep architectures, have three major drawbacks. First, they typically lack persuasive rationales to explain the outcomes of the models. Unexplainable predictions
Question routing (QR) aims at recommending newly posted questions to the potential answerers who are most likely to answer the questions. The existing approaches that learn users’ expertise from their past question-answering activities usually suffer from challenges in two aspects: 1) multi-faceted expertise
Given a network with the labels for a subset of nodes, transductive node classification targets to predict the labels for the remaining nodes in the network. This technique has been used in a variety of applications such as voxel functionality detection in brain network and group label prediction in
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
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
Node classification in graph-structured data aims to classify the nodes where labels are only available for a subset of nodes. This problem has attracted considerable research efforts in recent years. In real-world applications, both graph topology and node attributes evolve over time. Existing techniques,
Co-clustering partitions instances and features simultaneously by leveraging the duality between them, and it often yields impressive performance improvement over traditional clustering algorithms. The recent development in learning deep representations has demonstrated the advantage in extracting effective
Nowadays, multivariate time series data are increasingly collected in various real-world systems, e.g., power plants, wearable devices, etc. Anomaly detection and diagnosis in multivariate time series refer to identifying abnormal status in certain time steps and pinpointing the root causes. Building
Given a large number of low-quality heterogeneous categorical alerts collected from an anomaly detection system, how to characterize the complex relationships between different alerts and deliver trustworthy rankings to end users? While existing techniques focus on either mining alert patterns or filtering
Multivariate time series data are becoming increasingly common in numerous real-world applications, e.g., power plant monitoring, health care, wearable devices, automobiles, etc. As a result, multivariate time series retrieval, i.e., given the current multivariate time series segment, how to obtain its
The problem of network representation learning, also known as network embedding, arises in many machine learning tasks assuming that there exist a small number of variabilities in the vertex representations which can capture the “semantics” of the original network structure. Most existing network embedding
Massive and dynamic networks arise in many practical applications such as social media, security and public health. Given an evolutionary network, it is crucial to detect structural anomalies, such as vertices and edges whose “behaviors” deviate from underlying majority of the network, in a real-time
Unsupervised anomaly detection on multi- or high-dimensional data is of great importance in both fundamental machine learning research and industrial applications, for which density estimation lies at the core. Although previous approaches based on dimensionality reduction followed by density estimation
Network embedding aims to learn a low-dimensional vector representation for each node in the social and information networks, with the constraint to preserve network structures. Most existing methods focus on single network embedding, ignoring the relationship between multiple networks. In many real-world