Search Results for author:
Found 189 papers, 58 papers with code
A Survey on the Memory Mechanism of Large Language Model based Agents
Compared with original LLMs, LLM-based agents are featured in their self-evolving capability, which is the basis for solving real-world problems that need long-term and complex agent-environment interactions.
Single-temporal Supervised Remote Change Detection for Domain Generalization
In this paper, we propose a multimodal contrastive learning (ChangeCLIP) based on visual-language pre-training for change detection domain generalization.
Learn to Tour: Operator Design For Solution Feasibility Mapping in Pickup-and-delivery Traveling Salesman Problem
We make a comparison of our method and baselines, including classic OR algorithms and existing learning methods.
Leveraging Fine-Grained Information and Noise Decoupling for Remote Sensing Change Detection
Next, a shape-aware and a brightness-aware module are designed to improve the capacity for representation learning.
Cramer-Rao Bounds for Near-Field Sensing: A Generic Modular Architecture
A generic modular array architecture is proposed, featuring uniform/non-uniform subarray layouts that allows for flexible deployment.
RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm
For the model part, we adopt Generative Pre-training Transformer (GPT) as the sequential recommendation model and design a user modular to capture personalized information.
DMAD: Dual Memory Bank for Real-World Anomaly Detection
To address the challenge of real-world anomaly detection, we propose a new framework named Dual Memory bank enhanced representation learning for Anomaly Detection (DMAD).
Multiply Robust Estimation for Local Distribution Shifts with Multiple Domains
We focus on scenarios where data distributions vary across multiple segments of the entire population and only make local assumptions about the differences between training and test (deployment) distributions within each segment.
Large Language Model-based Human-Agent Collaboration for Complex Task Solving
We construct a human-agent collaboration dataset to train this policy model in an offline reinforcement learning environment.
DMCE: Diffusion Model Channel Enhancer for Multi-User Semantic Communication Systems
To address this, this paper proposes a diffusion model (DM)-based channel enhancer (DMCE) for improving the performance of multi-user semantic communication, with the DM learning the particular data distribution of channel effects on the transmitted semantic features.
Efficient Online Crowdsourcing with Complex Annotations
Crowdsourcing platforms use various truth discovery algorithms to aggregate annotations from multiple labelers.
M$^3$TN: Multi-gate Mixture-of-Experts based Multi-valued Treatment Network for Uplift Modeling
M$^3$TN consists of two components: 1) a feature representation module with Multi-gate Mixture-of-Experts to improve the efficiency; 2) a reparameterization module by modeling uplift explicitly to improve the effectiveness.
TAROT: A Hierarchical Framework with Multitask Co-Pretraining on Semi-Structured Data towards Effective Person-Job Fit
Person-job fit is an essential part of online recruitment platforms in serving various downstream applications like Job Search and Candidate Recommendation.
Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queries
We evaluate five state-of-the-art models using three different metrics and the results show that our benchmark presents introduces considerable challenge in the field of tabular data analysis, paving the way for more advanced research opportunities.
Professional Network Matters: Connections Empower Person-Job Fit
Online recruitment platforms typically employ Person-Job Fit models in the core service that automatically match suitable job seekers with appropriate job positions.
Spatial Deep Learning for Site-Specific Movement Optimization of Aerial Base Stations
Unmanned aerial vehicles (UAVs) can be utilized as aerial base stations (ABSs) to provide wireless connectivity for ground users (GUs) in various emergency scenarios.
Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models
Vision-Language Large Models (VLMs) have become primary backbone of AI, due to the impressive performance.
DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection
Reconstruction-based approaches have achieved remarkable outcomes in anomaly detection.
AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model
Existing anomaly inspection methods are limited in their performance due to insufficient anomaly data.
Enhancing Cross-domain Click-Through Rate Prediction via Explicit Feature Augmentation
Later the augmentation network employs the explicit cross-domain knowledge as augmented information to boost the target domain CTR prediction.
HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video
Since humans interact with diverse objects every day, the holistic 3D capture of these interactions is important to understand and model human behaviour.
Don't Make Your LLM an Evaluation Benchmark Cheater
Large language models~(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity.
DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset
Federated Learning (FL) is a distributed learning paradigm that can coordinate heterogeneous edge devices to perform model training without sharing private data.
TRANSOM: An Efficient Fault-Tolerant System for Training LLMs
As a result, A substantial amount of training time is devoted to task checkpoint saving and loading, task rescheduling and restart, and task manual anomaly checks, which greatly harms the overall training efficiency.
Fine-Grained Annotation for Face Anti-Spoofing
In this paper, we propose a fine-grained annotation method for face anti-spoofing.
Integrated Sensing and Communication Neighbor Discovery for MANET with Gossip Mechanism
In order to further reduce the convergence time of ND, this paper introduces the ISAC-enabled gossip mechanism into the ND algorithm.
Offline Imitation Learning with Variational Counterfactual Reasoning
We theoretically analyze the influence of the generated expert data and the improvement of generalization.
Text-to-Image Generation for Abstract Concepts
Recent years have witnessed the substantial progress of large-scale models across various domains, such as natural language processing and computer vision, facilitating the expression of concrete concepts.
Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption
To address these problems, we propose a novel phasic content fusing few-shot diffusion model with directional distribution consistency loss, which targets different learning objectives at distinct training stages of the diffusion model.
Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks
In this paper, we propose a framework of Roulette, which is a task-oriented semantic privacy-preserving collaborative inference framework for deep learning classifiers.
FedDD: Toward Communication-efficient Federated Learning with Differential Parameter Dropout
FedDD consists of two key modules: dropout rate allocation and uploaded parameter selection, which will optimize the model parameter uploading ratios tailored to different clients' heterogeneous conditions and also select the proper set of important model parameters for uploading subject to clients' dropout rate constraints.
A Survey on Large Language Model based Autonomous Agents
In this paper, we present a comprehensive survey of these studies, delivering a systematic review of the field of LLM-based autonomous agents from a holistic perspective.
ViCo: Engaging Video Comment Generation with Human Preference Rewards
Experiments on ViCo-20k show that the comments generated by our ViCo model exhibit the best performance in terms of both quantitative and qualitative results, particularly when engagement is considered.
Cloth2Tex: A Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On
Since traditional warping-based texture generation methods require a significant number of control points to be manually selected for each type of garment, which can be a time-consuming and tedious process.
A3D: Adaptive, Accurate, and Autonomous Navigation for Edge-Assisted Drones
Accurate navigation is of paramount importance to ensure flight safety and efficiency for autonomous drones.
Serving Graph Neural Networks With Distributed Fog Servers For Smart IoT Services
Graph Neural Networks (GNNs) have gained growing interest in miscellaneous applications owing to their outstanding ability in extracting latent representation on graph structures.
CMLM-CSE: Based on Conditional MLM Contrastive Learning for Sentence Embeddings
Traditional comparative learning sentence embedding directly uses the encoder to extract sentence features, and then passes in the comparative loss function for learning.
On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative Filtering
Graph CF has attracted more and more attention in recent years due to its effectiveness in leveraging high-order information in the user-item bipartite graph for better recommendations.
User Behavior Simulation with Large Language Model based Agents
Simulating high quality user behavior data has always been a fundamental problem in human-centered applications, where the major difficulty originates from the intricate mechanism of human decision process.
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
Embedding models have shown great power in knowledge graph completion (KGC) task.
Cross-domain Augmentation Networks for Click-Through Rate Prediction
The translation network is able to compute features from two domains with heterogeneous inputs separately by designing two independent branches, and then learn meaningful cross-domain knowledge using a designed cross-supervised feature translator.
Image to Multi-Modal Retrieval for Industrial Scenarios
We formally define a novel valuable information retrieval task: image-to-multi-modal-retrieval (IMMR), where the query is an image and the doc is an entity with both image and textual description.
AG3D: Learning to Generate 3D Avatars from 2D Image Collections
The key to progress is hence to learn generative models of 3D avatars from abundant unstructured 2D image collections.
Towards Carbon-Neutral Edge Computing: Greening Edge AI by Harnessing Spot and Future Carbon Markets
Provisioning dynamic machine learning (ML) inference as a service for artificial intelligence (AI) applications of edge devices faces many challenges, including the trade-off among accuracy loss, carbon emission, and unknown future costs.
Dually Enhanced Propensity Score Estimation in Sequential Recommendation
According to the graph, two complementary propensity scores are estimated from the views of item and user, respectively, based on the same set of user feedback data.
Learning to Detect Slip through Tactile Estimation of the Contact Force Field and its Entropy
Detection of slip during object grasping and manipulation plays a vital role in object handling.
REASONER: An Explainable Recommendation Dataset with Multi-aspect Real User Labeled Ground Truths Towards more Measurable Explainable Recommendation
To alleviate the above problems, we propose to build an explainable recommendation dataset with multi-aspect real user labeled ground truths.
Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition
Specifically, we define a temporally consistent human representation in canonical space and formulate a global optimization over the background model, the canonical human shape and texture, and per-frame human pose parameters.
Robust Mid-Pass Filtering Graph Convolutional Networks
Theoretical analyses guarantee the robustness of signals through the mid-pass filter, and we also shed light on the properties of different frequency signals under adversarial attacks.
Homophily-oriented Heterogeneous Graph Rewiring
To this end, we propose HDHGR, a homophily-oriented deep heterogeneous graph rewiring approach that modifies the HG structure to increase the performance of HGNN.
Fairness-aware Cross-Domain Recommendation
Cross-Domain Recommendation (CDR) is an effective way to alleviate the cold-start problem.
Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy
In more detail, penultimate layer outputs on the training set are considered as the representations of in-distribution (ID) data.
Ranked #11 on
Out-of-Distribution Detection
on ImageNet-1k vs Places
Real-Time High-Resolution Pedestrian Detection in Crowded Scenes via Parallel Edge Offloading
To identify dense and small-size pedestrians in surveillance systems, high-resolution cameras are widely deployed, where high-resolution images are captured and delivered to off-the-shelf pedestrian detection models.
HiFlash: Communication-Efficient Hierarchical Federated Learning with Adaptive Staleness Control and Heterogeneity-aware Client-Edge Association
Federated learning (FL) is a promising paradigm that enables collaboratively learning a shared model across massive clients while keeping the training data locally.
Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection
Specifically, we first propose a normality recall memory (NR Memory) to strengthen the normality of student-generated features by recalling the stored normal information.
Ranked #11 on
Anomaly Detection
on MVTec AD
InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds
To achieve this efficiency we propose a carefully designed and engineered system, that leverages emerging acceleration structures for neural fields, in combination with an efficient empty space-skipping strategy for dynamic scenes.
Coarse-to-Fine Contrastive Learning on Graphs
Inspired by the impressive success of contrastive learning (CL), a variety of graph augmentation strategies have been employed to learn node representations in a self-supervised manner.
Proximal Gradient-Based Unfolding for Massive Random Access in IoT Networks
Simulations show that the proposed unfolding neural network achieves better recovery performance, convergence rate, and adaptivity than current baselines.
Olive Branch Learning: A Topology-Aware Federated Learning Framework for Space-Air-Ground Integrated Network
The space-air-ground integrated network (SAGIN), one of the key technologies for next-generation mobile communication systems, can facilitate data transmission for users all over the world, especially in some remote areas where vast amounts of informative data are collected by Internet of remote things (IoRT) devices to support various data-driven artificial intelligence (AI) services.
Recent Advances in RecBole: Extensions with more Practical Considerations
In order to show the recent update in RecBole, we write this technical report to introduce our latest improvements on RecBole.
Fast-SNARF: A Fast Deformer for Articulated Neural Fields
A key challenge in making such methods applicable to articulated objects, such as the human body, is to model the deformation of 3D locations between the rest pose (a canonical space) and the deformed space.
Truthful Transaction Protocol for E-Commerce Networks Based on Double Auction
This screening algorithm is customer-oriented and offers personalized commodities by preventing unqualified sellers from participating in the transaction.
GNN at the Edge: Cost-Efficient Graph Neural Network Processing over Distributed Edge Servers
Edge intelligence has arisen as a promising computing paradigm for supporting miscellaneous smart applications that rely on machine learning techniques.
Recommendation with User Active Disclosing Willingness
Recommender system has been deployed in a large amount of real-world applications, profoundly influencing people's daily life and production. Traditional recommender models mostly collect as comprehensive as possible user behaviors for accurate preference estimation.
Multi-Modal Experience Inspired AI Creation
To model such human capabilities, in this paper, we define and solve a novel AI creation problem based on human experiences.
Debiased Recommendation with Neural Stratification
Debiased recommender models have recently attracted increasing attention from the academic and industry communities.
Neural Message Passing for Visual Relationship Detection
Visual relationship detection aims to detect the interactions between objects in an image; however, this task suffers from combinatorial explosion due to the variety of objects and interactions.
Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspective
To coordinate the selfish and heterogeneous participants, we propose a novel analytic framework for incentivizing effective and efficient collaborations for participant-centric FL.
Explainable Legal Case Matching via Inverse Optimal Transport-based Rationale Extraction
As an essential operation of legal retrieval, legal case matching plays a central role in intelligent legal systems.
RecBole 2.0: Towards a More Up-to-Date Recommendation Library
In order to support the study of recent advances in recommender systems, this paper presents an extended recommendation library consisting of eight packages for up-to-date topics and architectures.
Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking
Monocular image-based 3D perception has become an active research area in recent years owing to its applications in autonomous driving.
GraphAD: A Graph Neural Network for Entity-Wise Multivariate Time-Series Anomaly Detection
We also construct a real-world entity-wise multivariate time-series dataset from the business data of Ele. me.
FastRE: Towards Fast Relation Extraction with Convolutional Encoder and Improved Cascade Binary Tagging Framework
Recent work for extracting relations from texts has achieved excellent performance.
Working memory inspired hierarchical video decomposition with transformative representations
Video decomposition is very important to extract moving foreground objects from complex backgrounds in computer vision, machine learning, and medical imaging, e. g., extracting moving contrast-filled vessels from the complex and noisy backgrounds of X-ray coronary angiography (XCA).
Robust PCA Unrolling Network for Super-resolution Vessel Extraction in X-ray Coronary Angiography
Although robust PCA has been increasingly adopted to extract vessels from X-ray coronary angiography (XCA) images, challenging problems such as inefficient vessel-sparsity modelling, noisy and dynamic background artefacts, and high computational cost still remain unsolved.
Reinforcement Re-ranking with 2D Grid-based Recommendation Panels
Then, it defines \emph{the MDP discrete time steps as the ranks in the initial ranking list, and the actions as the prediction of the user-item preference and the selection of the slots}.
Sequential Recommendation with Causal Behavior Discovery
The key of sequential recommendation lies in the accurate item correlation modeling.
Sequential Recommendation with User Evolving Preference Decomposition
To solve this problem, in this paper, we propose a novel sequential recommender model via decomposing and modeling user independent preferences.
Knowledge-Guided Learning for Transceiver Design in Over-the-Air Federated Learning
Based on the convergence analysis, we formulate an optimization problem to minimize the upper bound to enhance the learning performance, followed by proposing an alternating optimization algorithm to facilitate the optimal transceiver design for AirComp-assisted FL.
A Unified Network Equilibrium for E-Hailing Platform Operation and Customer Mode Choice
This paper aims to combine both economic and network user equilibrium for ride-sourcing and ride-pooling services, while endogenously optimizing the pooling sequence of two origin-destination (OD) pairs.
3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs
In this paper, we propose a novel multi-level aggregation network to regress the coordinates of the vertices of a 3D face from a single 2D image in an end-to-end manner.
PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence
We present a novel method to learn Personalized Implicit Neural Avatars (PINA) from a short RGB-D sequence.
Generalizable Information Theoretic Causal Representation
It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems.
Measuring "Why" in Recommender Systems: a Comprehensive Survey on the Evaluation of Explainable Recommendation
Beyond summarizing the previous work, we also analyze the (dis)advantages of existing evaluation methods and provide a series of guidelines on how to select them.
Action Keypoint Network for Efficient Video Recognition
An effective approach is to select informative content from the holistic video, yielding a popular family of dynamic video recognition methods.
Ranked #42 on
Action Recognition
on Something-Something V1
Debiased Recommendation with User Feature Balancing
To alleviate these problems, in this paper, we propose a novel debiased recommendation framework based on user feature balancing.
Learning to Identify Top Elo Ratings: A Dueling Bandits Approach
The Elo rating system is widely adopted to evaluate the skills of (chess) game and sports players.
gDNA: Towards Generative Detailed Neural Avatars
Furthermore, we show that our method can be used on the task of fitting human models to raw scans, outperforming the previous state-of-the-art.
Edge Robotics: Edge-Computing-Accelerated Multi-Robot Simultaneous Localization and Mapping
With the wide penetration of smart robots in multifarious fields, Simultaneous Localization and Mapping (SLAM) technique in robotics has attracted growing attention in the community.
I M Avatar: Implicit Morphable Head Avatars from Videos
Traditional 3D morphable face models (3DMMs) provide fine-grained control over expression but cannot easily capture geometric and appearance details.
Learning Proximal Operator Methods for Massive Connectivity in IoT Networks
To mitigate all the aforementioned limitations, we in this paper develop an effective unfolding neural network framework built upon the proximal operator method to tackle the JADCE problem in IoT networks, where the base station is equipped with multiple antennas.
User behavior understanding in real world settings
It is necessary to learn a dynamic group of representations according the item groups in a user historical behavior.
Gumble Softmax For User Behavior Modeling
We propose a sequential model with dynamic number of representations for recommendation systems (RDRSR).
Source Free Unsupervised Graph Domain Adaptation
To address the non-trivial adaptation challenges in this practical scenario, we propose a model-agnostic algorithm called SOGA for domain adaptation to fully exploit the discriminative ability of the source model while preserving the consistency of structural proximity on the target graph.
Neuron with Steady Response Leads to Better Generalization
Based on the analysis results, we articulate the Neuron Steadiness Hypothesis: the neuron with similar responses to instances of the same class leads to better generalization.
Human Performance Capture from Monocular Video in the Wild
In this work, we propose a method capable of capturing the dynamic 3D human shape from a monocular video featuring challenging body poses, without any additional input.
Inhomogeneous Social Recommendation with Hypergraph Convolutional Networks
With the hypergraph convolutional networks, the social relations can be modeled in a more fine-grained manner, which more accurately depicts real users' preferences, and benefits the recommendation performance.
Render In-between: Motion Guided Video Synthesis for Action Interpolation
We propose to address these issues in a motion-guided frame-upsampling framework that is capable of producing realistic human motion and appearance.
SkullEngine: A Multi-stage CNN Framework for Collaborative CBCT Image Segmentation and Landmark Detection
We propose a multi-stage coarse-to-fine CNN-based framework, called SkullEngine, for high-resolution segmentation and large-scale landmark detection through a collaborative, integrated, and scalable JSD model and three segmentation and landmark detection refinement models.
Shape-aware Multi-Person Pose Estimation from Multi-View Images
In this paper we contribute a simple yet effective approach for estimating 3D poses of multiple people from multi-view images.
Ranked #16 on
3D Multi-Person Pose Estimation
on Shelf
3D Multi-Person Pose Estimation
Multi-Person Pose Estimation
Robust Cross-Modal Semi-supervised Few Shot Learning
Semi-supervised learning has been successfully applied to few-shot learning (FSL) due to its capability of leveraging the information of limited labeled data and massive unlabeled data.
Informative Robust Causal Representation for Generalizable Deep Learning
In many real-world scenarios, such as image classification and recommender systems, it is evidence that representation learning can improve model's performance over multiple downstream tasks.
A Self-Supervised Deep Framework for Reference Bony Shape Estimation in Orthognathic Surgical Planning
In the training stage, the simulator maps jaw deformities of a patient bone to a normal bone to generate a simulated deformed bone.
Top-N Recommendation with Counterfactual User Preference Simulation
To alleviate this problem, in this paper, we propose to reformulate the recommendation task within the causal inference framework, which enables us to counterfactually simulate user ranking-based preferences to handle the data scarce problem.
Counterfactual Explainable Recommendation
Technically, for each item recommended to each user, CountER formulates a joint optimization problem to generate minimal changes on the item aspects so as to create a counterfactual item, such that the recommendation decision on the counterfactual item is reversed.
Neuron Campaign for Initialization Guided by Information Bottleneck Theory
Initialization plays a critical role in the training of deep neural networks (DNN).
Enabling Long-Term Cooperation in Cross-Silo Federated Learning: A Repeated Game Perspective
We show that enforced by a punishment strategy, such a cooperative strategy is a subgame perfect Nash equilibrium (SPNE) of the infinitely repeated game, under which some clients who are free riders at the NE of the stage game choose to be (partial) contributors.
HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
In this work, we propose a high fidelity face swapping method, called HifiFace, which can well preserve the face shape of the source face and generate photo-realistic results.
Ranked #7 on
Face Swapping
on FaceForensics++
A Game-Theoretic Approach to Multi-Agent Trust Region Optimization
Trust region methods are widely applied in single-agent reinforcement learning problems due to their monotonic performance-improvement guarantee at every iteration.
TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning
With the rapid growth of traffic sensors deployed, a massive amount of traffic flow data are collected, revealing the long-term evolution of traffic flows and the gradual expansion of traffic networks.
TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data
To simultaneously extract spatial and relational information from tables, we propose a novel neural network architecture, TabularNet.
Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective
Network Embedding aims to learn a function mapping the nodes to Euclidean space contribute to multiple learning analysis tasks on networks.
Contrastive Attraction and Contrastive Repulsion for Representation Learning
We realize this strategy with contrastive attraction and contrastive repulsion (CACR), which makes the query not only exert a greater force to attract more distant positive samples but also do so to repel closer negative samples.
SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes
However, this is problematic since the backward warp field is pose dependent and thus requires large amounts of data to learn.
Generating Multi-scale Maps from Remote Sensing Images via Series Generative Adversarial Networks
The series strategy avoids RS-m inconsistency as inputs are high-resolution large-scale RSIs, and reduces the distribution gap in multi-scale map generation through similar pixel distributions among multi-scale maps.
Large-scale simultaneous inference under dependence
Simultaneous inference allows for the exploration of data while deciding on criteria for proclaiming discoveries.
Statistics Theory Methodology Statistics Theory
Causal Collaborative Filtering
However, pure correlative learning may lead to Simpson's paradox in predictions, and thus results in sacrificed recommendation performance.
Deep Reinforcement Learning with Spatio-temporal Traffic Forecasting for Data-Driven Base Station Sleep Control
To meet the ever increasing mobile traffic demand in 5G era, base stations (BSs) have been densely deployed in radio access networks (RANs) to increase the network coverage and capacity.
EC-SAGINs: Edge Computing-enhanced Space-Air-Ground Integrated Networks for Internet of Vehicles
After discussing several existing orbital and aerial edge computing architectures, we propose a framework of edge computing-enabled space-air-ground integrated networks (EC-SAGINs) to support various IoV services for the vehicles in remote areas.
Discrete Knowledge Graph Embedding based on Discrete Optimization
This paper proposes a discrete knowledge graph (KG) embedding (DKGE) method, which projects KG entities and relations into the Hamming space based on a computationally tractable discrete optimization algorithm, to solve the formidable storage and computation cost challenges in traditional continuous graph embedding methods.
Generate Natural Language Explanations for Recommendation
Motivated by this problem, we propose to generate free-text natural language explanations for personalized recommendation.
Multi-Agent Trust Region Learning
We derive the lower bound of agents' payoff improvements for MATRL methods, and also prove the convergence of our method on the meta-game fixed points.
Causal World Models by Unsupervised Deconfounding of Physical Dynamics
The capability of imagining internally with a mental model of the world is vitally important for human cognition.
Dynamic driving and routing games for autonomous vehicles on networks: A mean field game approach
In this paper, we aim to develop a game-theoretic model to solve for AVs's optimal driving strategies of velocity control in the interior of a road link and route choice at a junction node.
Autonomous Vehicles
Decision Making
Optimization and Control
Systems and Control
Systems and Control
FedHome: Cloud-Edge based Personalized Federated Learning for In-Home Health Monitoring
In this paper, we propose FedHome, a novel cloud-edge based federated learning framework for in-home health monitoring, which learns a shared global model in the cloud from multiple homes at the network edges and achieves data privacy protection by keeping user data locally.
CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices
CoEdge utilizes available computation and communication resources at the edge and dynamically partitions the DNN inference workload adaptive to devices' computing capabilities and network conditions.
TSSRGCN: Temporal Spectral Spatial Retrieval Graph Convolutional Network for Traffic Flow Forecasting
Further analysis indicates that the locality and globality of the traffic networks are critical to traffic flow prediction and the proposed TSSRGCN model can adapt to the various temporal traffic patterns.
Multi-Agent Reinforcement Learning for Markov Routing Games: A New Modeling Paradigm For Dynamic Traffic Assignment
We show that the routing behavior of intelligent agents is shown to converge to the classical notion of predictive dynamic user equilibrium (DUE) when traffic environments are simulated using dynamic loading models (DNL).
RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms
In this library, we implement 73 recommendation models on 28 benchmark datasets, covering the categories of general recommendation, sequential recommendation, context-aware recommendation and knowledge-based recommendation.
GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs
Most existing GNN models exploit a single type of aggregator (e. g., mean-pooling) to aggregate neighboring nodes information, and then add or concatenate the output of aggregator to the current representation vector of the center node.
Learning on Attribute-Missing Graphs
Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community.
Learning Euler's Elastica Model for Medical Image Segmentation
Inspired by Euler's Elastica model and recent active contour models introduced into the field of deep learning, we propose a novel active contour with elastica (ACE) loss function incorporating Elastica (curvature and length) and region information as geometrically-natural constraints for the image segmentation tasks.
CAFE: Coarse-to-Fine Neural Symbolic Reasoning for Explainable Recommendation
User profiles can capture prominent user behaviors from the history, and provide valuable signals about which kinds of path patterns are more likely to lead to potential items of interest for the user.
Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network
Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data.
When Deep Reinforcement Learning Meets Federated Learning: Intelligent Multi-Timescale Resource Management for Multi-access Edge Computing in 5G Ultra Dense Network
Ultra-dense edge computing (UDEC) has great potential, especially in the 5G era, but it still faces challenges in its current solutions, such as the lack of: i) efficient utilization of multiple 5G resources (e. g., computation, communication, storage and service resources); ii) low overhead offloading decision making and resource allocation strategies; and iii) privacy and security protection schemes.
Towards Equivalent Transformation of User Preferences in Cross Domain Recommendation
In this paper, we attempt to learn both features of user preferences in a more principled way.
Decoupled Variational Embedding for Signed Directed Networks
Comprehensive results on both link sign prediction and node recommendation task demonstrate the effectiveness of DVE.
Learning Node Representations against Perturbations
In this paper, we study how to learn node representations against perturbations in GNN.
Human Body Model Fitting by Learned Gradient Descent
We propose a novel algorithm for the fitting of 3D human shape to images.
Ranked #9 on
3D Human Pose Estimation
on EMDB
Category Level Object Pose Estimation via Neural Analysis-by-Synthesis
Many object pose estimation algorithms rely on the analysis-by-synthesis framework which requires explicit representations of individual object instances.
Dual Graph Embedding for Object-Tag LinkPrediction on the Knowledge Graph
Most existing methods focus on preserving the first-order proximity between entities in the KG.
Collaborative Adversarial Learning for RelationalLearning on Multiple Bipartite Graphs
The two-level alignment acts as two different constraints on different relations of the shared entities and facilitates better knowledge transfer for relational learning on multiple bipartite graphs.
Joint Multi-User DNN Partitioning and Computational Resource Allocation for Collaborative Edge Intelligence
With the assistance of edge servers, user equipments (UEs) are able to run deep neural network (DNN) based AI applications, which are generally resource-hungry and compute-intensive, such that an individual UE can hardly afford by itself in real time.
Learning Post-Hoc Causal Explanations for Recommendation
State-of-the-art recommender systems have the ability to generate high-quality recommendations, but usually cannot provide intuitive explanations to humans due to the usage of black-box prediction models.
Network Massive MIMO Transmission Over Millimeter-Wave and Terahertz Bands: Mobility Enhancement and Blockage Mitigation
Based on these insights, the network massive MIMO precoding design is reduced to a network sum-rate maximization problem with respect to beam domain power allocation.
Knowledge Distillation for Mobile Edge Computation Offloading
In this article, we propose an edge computation offloading framework based on Deep Imitation Learning (DIL) and Knowledge Distillation (KD), which assists end devices to quickly make fine-grained decisions to optimize the delay of computation tasks online.
XBlock-EOS: Extracting and Exploring Blockchain Data From EOSIO
It is challenging to process and analyze a high volume of raw EOSIO data and establish the mapping from original raw data to the well-grained datasets since it requires substantial efforts in extracting various types of data as well as sophisticated knowledge on software engineering and data analytics.
Computational Engineering, Finance, and Science Cryptography and Security
HierTrain: Fast Hierarchical Edge AI Learning with Hybrid Parallelism in Mobile-Edge-Cloud Computing
We develop a novel \textit{hybrid parallelism} method, which is the key to HierTrain, to adaptively assign the DNN model layers and the data samples across the three levels of edge device, edge server and cloud center.
DeepCP: Deep Learning Driven Cascade Prediction Based Autonomous Content Placement in Closed Social Network
Accordingly, we further propose a novel autonomous content placement mechanism CP-GAN which adopts the generative adversarial network (GAN) for agile placement decision making to reduce the content access latency and enhance users' QoE.
HFEL: Joint Edge Association and Resource Allocation for Cost-Efficient Hierarchical Federated Edge Learning
We further formulate a joint computation and communication resource allocation and edge association problem for device users under HFEL framework to achieve global cost minimization.
Distributed, Parallel, and Cluster Computing
Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework
Internet of Things (IoT) have widely penetrated in different aspects of modern life and many intelligent IoT services and applications are emerging.
Liability Design for Autonomous Vehicles and Human-Driven Vehicles: A Hierarchical Game-Theoretic Approach
The game is then simulated with numerical examples to investigate the emergence of human drivers' moral hazard, the AV manufacturer's role in traffic safety, and the law maker's role in liability design.
Cascading: Association Augmented Sequential Recommendation
Recently, recommendation according to sequential user behaviors has shown promising results in many application scenarios.
Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction
For the backbone, we propose multi-branch multi-scale graph convolution networks to extract spatial and temporal features.
Ranked #39 on
Skeleton Based Action Recognition
on NTU RGB+D
Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing
As a key technology of enabling Artificial Intelligence (AI) applications in 5G era, Deep Neural Networks (DNNs) have quickly attracted widespread attention.
Node Attribute Generation on Graphs
NANG learns a unifying latent representation which is shared by both node attributes and graph structures and can be translated to different modalities.
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Ubiquitous sensors and smart devices from factories and communities are generating massive amounts of data, and ever-increasing computing power is driving the core of computation and services from the cloud to the edge of the network.
A Survey on Neural Machine Reading Comprehension
Enabling a machine to read and comprehend the natural language documents so that it can answer some questions remains an elusive challenge.
Learning Active Contour Models for Medical Image Segmentation
Our aim was to tackle this limitation by developing a new model based on deep learning which takes into account the area inside as well as outside the region of interest as well as the size of boundaries during learning.
Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing
To this end, we conduct a comprehensive survey of the recent research efforts on edge intelligence.
Visually-aware Recommendation with Aesthetic Features
While recent developments on visually-aware recommender systems have taken the product image into account, none of them has considered the aesthetic aspect.
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
We validate AS-GCN in action recognition using two skeleton data sets, NTU-RGB+D and Kinetics.
Unpaired Pose Guided Human Image Generation
This paper studies the task of full generative modelling of realistic images of humans, guided only by coarse sketch of the pose, while providing control over the specific instance or type of outfit worn by the user.
Monocular Neural Image Based Rendering with Continuous View Control
The approach is self-supervised and only requires 2D images and associated view transforms for training.
Ramp-based Twin Support Vector Clustering
Traditional plane-based clustering methods measure the cost of within-cluster and between-cluster by quadratic, linear or some other unbounded functions, which may amplify the impact of cost.
Joint Representation Learning of Cross-lingual Words and Entities via Attentive Distant Supervision
Joint representation learning of words and entities benefits many NLP tasks, but has not been well explored in cross-lingual settings.
Robust Active Learning for Electrocardiographic Signal Classification
The classification of electrocardiographic (ECG) signals is a challenging problem for healthcare industry.
Variational Collaborative Learning for User Probabilistic Representation
Conventional CF-based methods use the user-item interaction data as the sole information source to recommend items to users.
In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning
In order to bring more intelligence to the edge systems, compared to traditional optimization methodology, and driven by the current deep learning techniques, we propose to integrate the Deep Reinforcement Learning techniques and Federated Learning framework with the mobile edge systems, for optimizing the mobile edge computing, caching and communication.
Aesthetic-based Clothing Recommendation
Considering that the aesthetic preference varies significantly from user to user and by time, we then propose a new tensor factorization model to incorporate the aesthetic features in a personalized manner.
Follow Me at the Edge: Mobility-Aware Dynamic Service Placement for Mobile Edge Computing
To address this challenge in terms of the performance-cost trade-off, in this paper we study the mobile edge service performance optimization problem under long-term cost budget constraint.
Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergy
As the backbone technology of machine learning, deep neural networks (DNNs) have have quickly ascended to the spotlight.
Topology Control for Energy-Efficient Localization in Mobile Underwater Sensor Networks using Stackelberg Game
In this game, the sensor node acts as a leader taking into account factors such as 'two-hop' anchor nodes and energy consumption, while anchor nodes act as multiple followers, considering their ability to localize sensor nodes and their energy consumption.
Networking and Internet Architecture
Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
Specifically, we propose a knowledge-base representation learning framework to embed heterogeneous entities for recommendation, and based on the embedded knowledge base, a soft matching algorithm is proposed to generate personalized explanations for the recommended items.
Ranked #3 on
Link Prediction
on Yelp
Explainable Recommendation: A Survey and New Perspectives
In this survey, we provide a comprehensive review for the explainable recommendation research.
Fictitious GAN: Training GANs with Historical Models
Inspired by the fictitious play learning process, a novel training method, referred to as Fictitious GAN, is introduced.
Learning over Knowledge-Base Embeddings for Recommendation
In this work, we propose to reason over knowledge base embeddings for personalized recommendation.
Superposition-Assisted Stochastic Optimization for Hawkes Processes
We consider the learning of multi-agent Hawkes processes, a model containing multiple Hawkes processes with shared endogenous impact functions and different exogenous intensities.
Training Generative Adversarial Networks via Primal-Dual Subgradient Methods: A Lagrangian Perspective on GAN
This formulation shows the connection between the standard GAN training process and the primal-dual subgradient methods for convex optimization.
Visually Explainable Recommendation
By this, we can not only provide recommendation results to the users, but also tell the users why an item is recommended by providing intuitive visual highlights in a personalized manner.
Texture Object Segmentation Based on Affine Invariant Texture Detection
To solve the issue of segmenting rich texture images, a novel detection methods based on the affine invariable principle is proposed.
Joint Representation Learning for Top-N Recommendation with Heterogeneous Information Sources
In this framework, each type of information source (review text, product image, numerical rating, etc) is adopted to learn the corresponding user and item representations based on available (deep) representation learning architectures.
Benefits from Superposed Hawkes Processes
The superposition of Hawkes processes is demonstrated to be beneficial for tightening the upper bound of excess risk under certain conditions, and we show the feasibility of the benefit in typical situations.
Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding
Integrating text and knowledge into a unified semantic space has attracted significant research interests recently.
Feedback-Controlled Sequential Lasso Screening
In this context, we propose and explore a feedback controlled sequential screening scheme.
Multi-lingual Geoparsing based on Machine Translation
Our results for geoparsing Chinese and Arabic text using our multi-lingual geoparsing method are comparable to our results for geoparsing English text with our English tools.
Deep Haar Scattering Networks
An orthogonal Haar scattering transform is a deep network, computed with a hierarchy of additions, subtractions and absolute values, over pairs of coefficients.
Unsupervised Deep Haar Scattering on Graphs
The classification of high-dimensional data defined on graphs is particularly difficult when the graph geometry is unknown.
Shrinkage Optimized Directed Information using Pictorial Structures for Action Recognition
In this paper, we propose a novel action recognition framework.
