Search Results for author:
Found 74 papers, 15 papers with code
Knowledge Graph Embedding by Translating on Hyperplanes
Utilizing the one-to-many/many-to-one mapping property of a relation, we propose a simple trick to reduce the possibility of false negative labeling.
Detecting and Explaining Causes From Text For a Time Series Event
Our quantitative and human analysis show empirical evidence that our method successfully extracts meaningful causality relationships between time series with textual features and generates appropriate explanation between them.
Correlated Anomaly Detection from Large Streaming Data
Correlated anomaly detection (CAD) from streaming data is a type of group anomaly detection and an essential task in useful real-time data mining applications like botnet detection, financial event detection, industrial process monitor, etc.
Fast Botnet Detection From Streaming Logs Using Online Lanczos Method
Botnet, a group of coordinated bots, is becoming the main platform of malicious Internet activities like DDOS, click fraud, web scraping, spam/rumor distribution, etc.
Unifying Topic, Sentiment & Preference in an HDP-Based Rating Regression Model for Online Reviews
TSPRA combines topics (i. e. product aspects), word sentiment and user preference as regression factors, and is able to perform topic clustering, review rating prediction, sentiment analysis and what we invent as "critical aspect" analysis altogether in one framework.
Large-Scale Joint Topic, Sentiment & User Preference Analysis for Online Reviews
This paper presents a non-trivial reconstruction of a previous joint topic-sentiment-preference review model TSPRA with stick-breaking representation under the framework of variational inference (VI) and stochastic variational inference (SVI).
Creating Navigable Space from Sparse Noisy Map Points
We present a framework for creating navigable space from sparse and noisy map points generated by sparse visual SLAM methods.
Robotics
Optimizing Information Freshness in a Multiple Access Channel with Heterogeneous Devices
We formulate an optimization problem that aims at minimizing the average age of information (AoI) of the EH node subject to the queue stability condition of the grid-connected node.
Information Theory Networking and Internet Architecture Information Theory
An Ontology-driven Treatment Article Retrieval System for Precision Oncology
This paper presents an ontology-driven treatment article retrieval system developed and experimented using the data and ground truths provided by the TREC 2017 precision medicine track.
Pre-Training for Query Rewriting in A Spoken Language Understanding System
Then, inspired by the wide success of pre-trained contextual language embeddings, and also as a way to compensate for insufficient QR training data, we propose a language-modeling (LM) based approach to pre-train query embeddings on historical user conversation data with a voice assistant.
Neural Stochastic Block Model & Scalable Community-Based Graph Learning
Compared with SBM, our framework is flexible, naturally allows soft labels and digestion of complex node attributes.
Hybrid Ranking Network for Text-to-SQL
In this paper, we study how to leverage pre-trained language models in Text-to-SQL.
SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
We open-source the SMARTS platform and the associated benchmark tasks and evaluation metrics to encourage and empower research on multi-agent learning for autonomous driving.
ForceReader: a BERT-based Interactive Machine Reading Comprehension Model with Attention Separation
First, ForceReader proposes a novel solution called the Attention Separation Representation to respond to attention deconcentration.
Time-Optimal Guidance to Intercept Moving Targets by Dubins Vehicles
When the target's velocity is constant, by employing the geometric properties, those 4 candidates are transformed to a class of sufficiently smooth real-valued functions.
Optimization and Control
Consensus-Based Distributed Computation of Link-Based Network Metrics
Average consensus algorithms have wide applications in distributed computing systems where all the nodes agree on the average value of their initial states by only exchanging information with their local neighbors.
Distributed Computing
Distributed, Parallel, and Cluster Computing
Social and Information Networks
Signal Processing
Self-Supervised Transfer Learning for Hand Mesh Recovery From Binocular Images
Traditional methods for RGB hand mesh recovery usually need to train a separate model for each dataset with the corresponding ground truth and are hardly adapted to new scenarios without the ground truth for supervision.
Theoretical analysis on the transient ignition of premixed expanding flame in a quiescent mixture
It is found that as the heating power grows, the memory effect becomes increasingly important and it can greatly reduce the minimum ignition energy.
Fluid Dynamics
SPSA-Based Successive Beamforming for Mobile Satellite Receivers with Phased Arrays
Efficient and low-complexity beamforming design is an important element of satellite communication systems with mobile receivers equipped with phased arrays.
Device Scheduling and Update Aggregation Policies for Asynchronous Federated Learning
Federated Learning (FL) is a newly emerged decentralized machine learning (ML) framework that combines on-device local training with server-based model synchronization to train a centralized ML model over distributed nodes.
Polyline Generative Navigable Space Segmentation for Autonomous Visual Navigation
Detecting navigable space is a fundamental capability for mobile robots navigating in unknown or unmapped environments.
On-Demand AoI Minimization in Resource-Constrained Cache-Enabled IoT Networks with Energy Harvesting Sensors
We consider a resource-constrained IoT network, where multiple users make on-demand requests to a cache-enabled edge node to send status updates about various random processes, each monitored by an energy harvesting sensor.
Adaptive Spike-Like Representation of EEG Signals for Sleep Stages Scoring
Recently there has seen promising results on automatic stage scoring by extracting spatio-temporal features from electroencephalogram (EEG).
Cancer Subtyping via Embedded Unsupervised Learning on Transcriptomics Data
In this paper, we propose to investigate automatic subtyping from an unsupervised learning perspective by directly constructing the underlying data distribution itself, hence sufficient data can be generated to alleviate the issue of overfitting.
Automated Sleep Staging via Parallel Frequency-Cut Attention
This paper proposes a novel framework for automatically capturing the time-frequency nature of electroencephalogram (EEG) signals of human sleep based on the authoritative sleep medicine guidance.
Multi-Tier Platform for Cognizing Massive Electroencephalogram
A spiking neural network (SNN) based tier is designed to distill the principle information in terms of spike-streams from the rare features, which maintains the temporal implication in the nature of EEGs.
Multi-Target Active Object Tracking with Monte Carlo Tree Search and Target Motion Modeling
In this work, we are dedicated to multi-target active object tracking (AOT), where there are multiple targets as well as multiple cameras in the environment.
Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning
Maximum Tsallis entropy (MTE) framework in reinforcement learning has gained popularity recently by virtue of its flexible modeling choices including the widely used Shannon entropy and sparse entropy.
$q$-Munchausen Reinforcement Learning
The recently successful Munchausen Reinforcement Learning (M-RL) features implicit Kullback-Leibler (KL) regularization by augmenting the reward function with logarithm of the current stochastic policy.
Automated Cancer Subtyping via Vector Quantization Mutual Information Maximization
Cancer subtyping is crucial for understanding the nature of tumors and providing suitable therapy.
Generative Adversarial Networks Based on Transformer Encoder and Convolution Block for Hyperspectral Image Classification
Nowadays, HSI classification can reach a high classification accuracy when given sufficient labeled samples as training set.
Cancer Subtyping by Improved Transcriptomic Features Using Vector Quantized Variational Autoencoder
As such, existing methods often impose unrealistic assumptions to extract useful features from the data while avoiding overfitting to spurious correlations.
StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hints
Neural Radiance Fields (NeRF) achieve photo-realistic view synthesis with densely captured input images.
Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations
In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server at the same time.
Cross Aggregation Transformer for Image Restoration
The core of our CAT is the Rectangle-Window Self-Attention (Rwin-SA), which utilizes horizontal and vertical rectangle window attention in different heads parallelly to expand the attention area and aggregate the features cross different windows.
Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networks
Federated Learning (FL) is a collaborative machine learning (ML) framework that combines on-device training and server-based aggregation to train a common ML model among distributed agents.
HSE: Hybrid Species Embedding for Deep Metric Learning
Deep metric learning is crucial for finding an embedding function that can generalize to training and testing data, including unknown test classes.
Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence
Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly.
KG-ECO: Knowledge Graph Enhanced Entity Correction for Query Rewriting
Query Rewriting (QR) plays a critical role in large-scale dialogue systems for reducing frictions.
Drugs Resistance Analysis from Scarce Health Records via Multi-task Graph Representation
In this paper, we propose a novel framework for rapid clinical intervention by viewing health records as graphs whose nodes are mapped from medical events and edges as correspondence between events in given a time window.
SePaint: Semantic Map Inpainting via Multinomial Diffusion
Prediction beyond partial observations is crucial for robots to navigate in unknown environments because it can provide extra information regarding the surroundings beyond the current sensing range or resolution.
IDA: Informed Domain Adaptive Semantic Segmentation
To improve the UDA-SS performance, we propose an Informed Domain Adaptation (IDA) model, a self-training framework that mixes the data based on class-level segmentation performance, which aims to emphasize small-region semantics during mixup.
Recursive Generalization Transformer for Image Super-Resolution
In this work, we propose the Recursive Generalization Transformer (RGT) for image SR, which can capture global spatial information and is suitable for high-resolution images.
Ranked #5 on
Image Super-Resolution
on Manga109 - 4x upscaling
Dynamic Scheduling for Federated Edge Learning with Streaming Data
In this work, we consider a Federated Edge Learning (FEEL) system where training data are randomly generated over time at a set of distributed edge devices with long-term energy constraints.
PALR: Personalization Aware LLMs for Recommendation
Then we adopt a LLM-based ranking model to generate recommended items.
Decentralized Learning over Wireless Networks: The Effect of Broadcast with Random Access
In particular, we investigate the impact of broadcast transmission and probabilistic random access policy on the convergence performance of D-SGD, considering the broadcast nature of wireless channels and the link dynamics in the communication topology.
Hierarchical Integration Diffusion Model for Realistic Image Deblurring
Specifically, we perform the DM in a highly compacted latent space to generate the prior feature for the deblurring process.
Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding
This paper presents our "Collaborative Query Rewriting" approach, which specifically addresses the task of rewriting new user interactions that have not been previously observed in the user's history.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+9
PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas
Unlike generalizable radiance fields trained on perspective images, PanoGRF avoids the information loss from panorama-to-perspective conversion and directly aggregates geometry and appearance features of 3D sample points from each panoramic view based on spherical projection.
Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting
The application of machine learning models to financial time series comes with several challenges, including the difficulty in cross-sequence reasoning and inference, the hurdle of incorporating multi-modal signals from historical news, financial knowledge graphs, etc., and the issue of interpreting and explaining the model results.
Pseudo-Trilateral Adversarial Training for Domain Adaptive Traversability Prediction
We prove that our CALI model -- a pseudo-trilateral game structure is advantageous over existing bilateral game structures.
Dual Aggregation Transformer for Image Super-Resolution
Based on the above idea, we propose a novel Transformer model, Dual Aggregation Transformer (DAT), for image SR. Our DAT aggregates features across spatial and channel dimensions, in the inter-block and intra-block dual manner.
Ranked #6 on
Image Super-Resolution
on Manga109 - 4x upscaling
MoCLIM: Towards Accurate Cancer Subtyping via Multi-Omics Contrastive Learning with Omics-Inference Modeling
Precision medicine fundamentally aims to establish causality between dysregulated biochemical mechanisms and cancer subtypes.
RecMind: Large Language Model Powered Agent For Recommendation
While the recommendation system (RS) has advanced significantly through deep learning, current RS approaches usually train and fine-tune models on task-specific datasets, limiting their generalizability to new recommendation tasks and their ability to leverage external knowledge due to model scale and data size constraints.
Over-the-Air Federated Learning with Compressed Sensing: Is Sparsification Necessary?
Over-the-Air (OtA) Federated Learning (FL) refers to an FL system where multiple agents apply OtA computation for transmitting model updates to a common edge server.
Decentralized Learning over Wireless Networks with Broadcast-Based Subgraph Sampling
This work centers on the communication aspects of decentralized learning over wireless networks, using consensus-based decentralized stochastic gradient descent (D-SGD).
Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers
Furthermore, our approach surpasses the performance of existing supervised methods like monoT5 and is on par with the state-of-the-art zero-shot methods.
Image Super-Resolution with Text Prompt Diffusion
Specifically, we first design a text-image generation pipeline to integrate text into the SR dataset through the text degradation representation and degradation model.
STADEE: STAtistics-based DEEp Detection of Machine Generated Text
We present STADEE, a \textbf{STA}tistics-based \textbf{DEE}p detection method to identify machine-generated text, addressing the limitations of current methods that rely heavily on fine-tuning pre-trained language models (PLMs).
PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields
Through extensive experiments, we demonstrate the effectiveness of PlanarNeRF in various scenarios and remarkable improvement over existing works.
Zero-Shot Position Debiasing for Large Language Models
Existing debiasing methods for LLMs require external bias knowledge or annotated non-biased samples, which is lacking for position debiasing and impractical in reality.
Training a General Spiking Neural Network with Improved Efficiency and Minimum Latency
This paper proposes a general training framework that enhances feature learning and activation efficiency within a limited time step, providing a new solution for more energy-efficient SNNs.
Faster Convergence with Less Communication: Broadcast-Based Subgraph Sampling for Decentralized Learning over Wireless Networks
Consensus-based decentralized stochastic gradient descent (D-SGD) is a widely adopted algorithm for decentralized training of machine learning models across networked agents.
Improving Building Temperature Forecasting: A Data-driven Approach with System Scenario Clustering
For smart energy management in buildings, usage patterns and their resulting profiles allow the improvement of control systems with prediction capabilities.
NARUTO: Neural Active Reconstruction from Uncertain Target Observations
We present NARUTO, a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning, enabling high-fidelity surface reconstruction.
Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection
Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming.
Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs
Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts.
Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation
Seq2seq language generation models that are trained offline with multiple domains in a sequential fashion often suffer from catastrophic forgetting.
Personalized Search-based Query Rewrite System for Conversational AI
Query rewrite (QR) is an emerging component in conversational AI systems, reducing user defect.
CATAMARAN: A Cross-lingual Long Text Abstractive Summarization Dataset
Cross-lingual summarization, which produces the summary in one language from a given source document in another language, could be extremely helpful for humans to obtain information across the world.
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
