Search Results for author:
Found 50 papers, 25 papers with code
When does Further Pre-training MLM Help? An Empirical Study on Task-Oriented Dialog Pre-training
Further pre-training language models on in-domain data (domain-adaptive pre-training, DAPT) or task-relevant data (task-adaptive pre-training, TAPT) before fine-tuning has been shown to improve downstream tasks’ performances.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
Semi-supervised Semantics-guided Adversarial Training for Trajectory Prediction
Predicting the trajectories of surrounding objects is a critical task in self-driving and many other autonomous systems.
Heterformer: A Transformer Architecture for Node Representation Learning on Heterogeneous Text-Rich Networks
We study node representation learning on heterogeneous text-rich networks, where nodes and edges are multi-typed and some types of nodes are associated with text information.
Augmentation-Free Graph Contrastive Learning with Performance Guarantee
Graph contrastive learning (GCL) is the most representative and prevalent self-supervised learning approach for graph-structured data.
Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encoding
The robustness of deep neural networks has received significant interest recently, especially when being deployed in safety-critical systems, as it is important to analyze how sensitive the model output is under input perturbations.
Federated Class-Incremental Learning
It makes the global model suffer from significant catastrophic forgetting on old classes in real-world scenarios, where local clients often collect new classes continuously and have very limited storage memory to store old classes.
Continual Prompt Tuning for Dialog State Tracking
A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle.
Shift-Robust Node Classification via Graph Adversarial Clustering
Then a shift-robust classifier is optimized on training graph and adversarial samples on target graph, which are generated by cluster GNN.
TAE: A Semi-supervised Controllable Behavior-aware Trajectory Generator and Predictor
Our model addresses trajectory generation and prediction in a unified architecture and benefits both tasks: the model can generate diverse, controllable and realistic trajectories to enhance planner optimization in safety-critical and long-tailed scenarios, and it can provide prediction of critical behavior in addition to the final trajectories for decision making.
Joint Differentiable Optimization and Verification for Certified Reinforcement Learning
In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e. g., safety, stability) under the learned controller.
Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data
In this work we present a method, Shift-Robust GNN (SR-GNN), designed to account for distributional differences between biased training data and the graph's true inference distribution.
Co-designing Intelligent Control of Building HVACs and Microgrids
Building loads consume roughly 40% of the energy produced in developed countries, a significant part of which is invested towards building temperature-control infrastructure.
Learning-based Framework for Sensor Fault-Tolerant Building HVAC Control with Model-assisted Learning
As people spend up to 87% of their time indoors, intelligent Heating, Ventilation, and Air Conditioning (HVAC) systems in buildings are essential for maintaining occupant comfort and reducing energy consumption.
POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systems
We propose POLAR, a \textbf{pol}ynomial \textbf{ar}ithmetic framework that leverages polynomial overapproximations with interval remainders for bounded-time reachability analysis of neural network-controlled systems (NNCSs).
Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization
Our NTL-based authorization approach instead provides data-centric protection, which we call applicability authorization, by significantly degrading the performance of the model on unauthorized data.
Verification in the Loop: Correct-by-Construction Control Learning with Reach-avoid Guarantees
Specifically, we leverage the verification results (computed reachable set of the system state) to construct feedback metrics for control learning, which measure how likely the current design of control parameters can meet the required reach-avoid property for safety and goal-reaching.
Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads
Based on this observation, we design a dynamic chopping module that can automatically remove heads and layers of the VisualBERT at an instance level when dealing with different questions.
End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering
The experiment results demonstrate that our approach can effectively mitigate the impact of adversarial attacks and can achieve 55% to 90% improvement over the original OpenPilot.
Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotator
Data quantity and quality are crucial factors for data-driven learning methods.
Securing Connected Vehicle Applications with an Efficient Dual Cyber-Physical Blockchain Framework
While connected vehicle (CV) applications have the potential to revolutionize traditional transportation system, cyber and physical attacks on them could be devastating.
Cryptography and Security
Weak Adaptation Learning: Addressing Cross-Domain Data Insufficiency With Weak Annotator
Data quantity and quality are crucial factors for data-driven learning methods.
Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps
Texts appearing in daily scenes that can be recognized by OCR (Optical Character Recognition) tools contain significant information, such as street name, product brand and prices.
Overview of the Ninth Dialog System Technology Challenge: DSTC9
Interactive evaluation of dialog, and 4.
Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization
Graph neural networks (GNNs) have achieved superior performance in various applications, but training dedicated GNNs can be costly for large-scale graphs.
Addressing Class Imbalance in Federated Learning
Our experiments demonstrate the importance of acknowledging class imbalance and taking measures as early as possible in FL training, and the effectiveness of our method in mitigating the impact.
Distributed Multi-agent Video Fast-forwarding
In many intelligent systems, a network of agents collaboratively perceives the environment for better and more efficient situation awareness.
One for Many: Transfer Learning for Building HVAC Control
Traditional HVAC control methods are typically based on creating explicit physical models for building thermal dynamics, which often require significant effort to develop and are difficult to achieve sufficient accuracy and efficiency for runtime building control and scalability for field implementations.
Unsupervised Differentiable Multi-aspect Network Embedding
To capture the multiple aspects of each node, existing studies mainly rely on offline graph clustering performed prior to the actual embedding, which results in the cluster membership of each node (i. e., node aspect distribution) fixed throughout training of the embedding model.
Structured Multimodal Attentions for TextVQA
In this paper, we propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above.
Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation
There is a growing interest in developing goal-oriented dialog systems which serve users in accomplishing complex tasks through multi-turn conversations.
Recent Advances and Challenges in Task-oriented Dialog System
Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities.
CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset.
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.
Eavesdrop the Composition Proportion of Training Labels in Federated Learning
Federated learning (FL) has recently emerged as a new form of collaborative machine learning, where a common model can be learned while keeping all the training data on local devices.
Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity
Extensive experiments on two large real-world datasets demonstrate the effectiveness of HyperMine and the utility of modeling context granularity.
Facet-Aware Evaluation for Extractive Summarization
In this paper, we present a facet-aware evaluation setup for better assessment of the information coverage in extracted summaries.
MaskPlus: Improving Mask Generation for Instance Segmentation
Instance segmentation is a promising yet challenging topic in computer vision.
ReachNN: Reachability Analysis of Neural-Network Controlled Systems
In this work, we propose a new reachability analysis approach based on Bernstein polynomials that can verify neural-network controlled systems with a more general form of activation functions, i. e., as long as they ensure that the neural networks are Lipschitz continuous.
Task-Guided Pair Embedding in Heterogeneous Network
In this paper, we propose a novel task-guided pair embedding framework in heterogeneous network, called TaPEm, that directly models the relationship between a pair of nodes that are related to a specific task (e. g., paper-author relationship in author identification).
ConvLab: Multi-Domain End-to-End Dialog System Platform
We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments.
Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks
To cope with the challenges in the comprehensive transcription of HINs, we propose the HEER algorithm, which embeds HINs via edge representations that are further coupled with properly-learned heterogeneous metrics.
FFNet: Video Fast-Forwarding via Reinforcement Learning
The first group is supported by video summarization techniques, which require processing of the entire video to select an important subset for showing to users.
Integrating Local Context and Global Cohesiveness for Open Information Extraction
However, current Open IE systems focus on modeling local context information in a sentence to extract relation tuples, while ignoring the fact that global statistics in a large corpus can be collectively leveraged to identify high-quality sentence-level extractions.
Expert Finding in Heterogeneous Bibliographic Networks with Locally-trained Embeddings
We study the task of expert finding in heterogeneous bibliographical networks based on two aspects: textual content analysis and authority ranking.
AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks
Therefore, we are motivated to propose a novel embedding learning framework---AspEm---to preserve the semantic information in HINs based on multiple aspects.
Deep Reinforcement Learning: Framework, Applications, and Embedded Implementations
The recent breakthroughs of deep reinforcement learning (DRL) technique in Alpha Go and playing Atari have set a good example in handling large state and actions spaces of complicated control problems.
Heterogeneous Supervision for Relation Extraction: A Representation Learning Approach
These annotations, referred as heterogeneous supervision, often conflict with each other, which brings a new challenge to the original relation extraction task: how to infer the true label from noisy labels for a given instance.
Adaptive Algorithm and Platform Selection for Visual Detection and Tracking
In this paper, we focus on this problem and propose a framework to adaptively select the "best" algorithm-parameter combination and the computation platform under performance and cost constraints at design time, and adapt the algorithms at runtime based on real-time inputs.
