Search Results for author:
Found 179 papers, 44 papers with code
AntDT: A Self-Adaptive Distributed Training Framework for Leader and Straggler Nodes
Previous works only address part of the stragglers and could not adaptively solve various stragglers in practice.
AntBatchInfer: Elastic Batch Inference in the Kubernetes Cluster
Offline batch inference is a common task in the industry for deep learning applications, but it can be challenging to ensure stability and performance when dealing with large amounts of data and complicated inference pipelines.
Unsupervised Band Selection Using Fused HSI and LiDAR Attention Integrating With Autoencoder
These approaches overlook the potential benefits of integrating multiple data sources, such as Light Detection and Ranging (LiDAR), and is further challenged by the limited availability of labeled data in HSI processing, which represents a significant obstacle.
LiDAR-Guided Cross-Attention Fusion for Hyperspectral Band Selection and Image Classification
The fusion of hyperspectral and LiDAR data has been an active research topic.
AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation
Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs.
HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multitask Learning
In this paper, we propose a neural network model to address multiple tasks jointly upon the input of 3D protein structures.
HSIMamba: Hyperpsectral Imaging Efficient Feature Learning with Bidirectional State Space for Classification
HSIMamba is designed to process data bidirectionally, significantly enhancing the extraction of spectral features and integrating them with spatial information for comprehensive analysis.
Breaking the Length Barrier: LLM-Enhanced CTR Prediction in Long Textual User Behaviors
However, we argue that a critical obstacle remains in deploying LLMs for practical use: the efficiency of LLMs when processing long textual user behaviors.
Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential Recommendation
Subsequently, we employ self-distillation to facilitate the transfer of knowledge from users with extensive behaviors (teachers) to users with limited behaviors (students).
Empowering Sequential Recommendation from Collaborative Signals and Semantic Relatedness
It is also significant to model the \textit{semantic relatedness} reflected in content features, e. g., images and text.
DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization
Our motivation stems from the highly efficient representation and surprising quality of the recent 3D Gaussian Splatting, despite it will encounter a geometry degradation when input views decrease.
Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum Learning
In this paper, we fill in this gap by proposing a motif-preserving Graph Neural Network with curriculum learning (MotifGNN) to jointly learn the lower-order structures from the original graph and higherorder structures from multi-view motif-based graphs for financial default prediction.
Graph Neural Network with Two Uplift Estimators for Label-Scarcity Individual Uplift Modeling
The estimator is general for all types of outcomes, and is able to comprehensively model the treatment and control group data together to approach the uplift.
ChatUIE: Exploring Chat-based Unified Information Extraction using Large Language Models
This motivated us to explore domain-specific modeling in chat-based language models as a solution for extracting structured information from natural language.
Can Small Language Models be Good Reasoners for Sequential Recommendation?
We encode the generated rationales from the student model into a dense vector, which empowers recommendation in both ID-based and ID-agnostic scenarios.
Resolution-Agnostic Neural Compression for High-Fidelity Portrait Video Conferencing via Implicit Radiance Fields
In this paper, we propose a novel low bandwidth neural compression approach for high-fidelity portrait video conferencing using implicit radiance fields to achieve both major objectives.
CMNER: A Chinese Multimodal NER Dataset based on Social Media
Multimodal Named Entity Recognition (MNER) is a pivotal task designed to extract named entities from text with the support of pertinent images.
Enhancing Zero-shot Counting via Language-guided Exemplar Learning
Recently, Class-Agnostic Counting (CAC) problem has garnered increasing attention owing to its intriguing generality and superior efficiency compared to Category-Specific Counting (CSC).
MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction
The stock market is a crucial component of the financial system, but predicting the movement of stock prices is challenging due to the dynamic and intricate relations arising from various aspects such as economic indicators, financial reports, global news, and investor sentiment.
G-Meta: Distributed Meta Learning in GPU Clusters for Large-Scale Recommender Systems
However, the existing systems are not tailored for meta learning based DLRM models and have critical problems regarding efficiency in distributed training in the GPU cluster.
GLISP: A Scalable GNN Learning System by Exploiting Inherent Structural Properties of Graphs
As a powerful tool for modeling graph data, Graph Neural Networks (GNNs) have received increasing attention in both academia and industry.
XUAT-Copilot: Multi-Agent Collaborative System for Automated User Acceptance Testing with Large Language Model
In past years, we have been dedicated to automating user acceptance testing (UAT) process of WeChat Pay, one of the most influential mobile payment applications in China.
A Comprehensive Study of Knowledge Editing for Large Language Models
In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches.
Ranked #1 on
knowledge editing
on zsRE
(using extra training data)
Hyperspectral Image Denoising via Spatial-Spectral Recurrent Transformer
This block consists of a spatial branch and a spectral branch.
GazeCLIP: Towards Enhancing Gaze Estimation via Text Guidance
Over the past decade, visual gaze estimation has garnered growing attention within the research community, thanks to its wide-ranging application scenarios.
An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training
Furthermore, our framework provides a simple user interface and allows for the agile allocation of models across devices in a fine-grained manner for various training scenarios, involving models of varying sizes and devices of different scales.
Making Large Language Models Better Knowledge Miners for Online Marketing with Progressive Prompting Augmentation
In this paper, we seek to carefully prompt a Large Language Model (LLM) with domain-level knowledge as a better marketing-oriented knowledge miner for marketing-oriented knowledge graph construction, which is however non-trivial, suffering from several inevitable issues in real-world marketing scenarios, i. e., uncontrollable relation generation of LLMs, insufficient prompting ability of a single prompt, the unaffordable deployment cost of LLMs.
Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction
In particular, we elaborately devise a Meta-learning Supported Teacher-student GNN (MST-GNN) that is not only built upon teacher-student architecture for alleviating the migration between "easy" and "hard" samples but also equipped with a meta learning based sample re-weighting module for helping the student GNN distinguish "hard" samples in a fine-grained manner.
PEACE: Prototype lEarning Augmented transferable framework for Cross-domain rEcommendation
To help merchants/customers to provide/access a variety of services through miniapps, online service platforms have occupied a critical position in the effective content delivery, in which how to recommend items in the new domain launched by the service provider for customers has become more urgent.
Hy-Tracker: A Novel Framework for Enhancing Efficiency and Accuracy of Object Tracking in Hyperspectral Videos
Hyperspectral object tracking has recently emerged as a topic of great interest in the remote sensing community.
Which Matters Most in Making Fund Investment Decisions? A Multi-granularity Graph Disentangled Learning Framework
In this paper, we highlight that both conformity and risk preference matter in making fund investment decisions beyond personal interest and seek to jointly characterize these aspects in a disentangled manner.
OptScaler: A Hybrid Proactive-Reactive Framework for Robust Autoscaling in the Cloud
The reactive module provides a self-tuning estimator of CPU utilization to the optimization model.
One Model for All: Large Language Models are Domain-Agnostic Recommendation Systems
We expect that by mixing the user's behaviors across different domains, we can exploit the common knowledge encoded in the pre-trained language model to alleviate the problems of data sparsity and cold start problems.
Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt
In this work, we first investigate such anytime fine-tuning effectiveness of existing continual pre-training approaches, concluding with unanimously decreased performance on unseen domains.
Rethinking Memory and Communication Cost for Efficient Large Language Model Training
In this paper, we rethink the impact of memory consumption and communication costs on the training speed of large language models, and propose a memory-communication balanced strategy set Partial Redundancy Optimizer (PaRO).
Data-Centric Financial Large Language Models
Large language models (LLMs) show promise for natural language tasks but struggle when applied directly to complex domains like finance.
Long-tail Augmented Graph Contrastive Learning for Recommendation
To make the data augmentation schema learnable, we design an auto drop module to generate pseudo-tail nodes from head nodes and a knowledge transfer module to reconstruct the head nodes from pseudo-tail nodes.
Enhancing Asynchronous Time Series Forecasting with Contrastive Relational Inference
Asynchronous time series, also known as temporal event sequences, are the basis of many applications throughout different industries.
AntM$^{2}$C: A Large Scale Dataset For Multi-Scenario Multi-Modal CTR Prediction
3) AntM$^{2}$C provides 1 billion CTR data with 200 features, including 200 million users and 6 million items.
Enhancing Recommender Systems with Large Language Model Reasoning Graphs
In this paper, we propose a novel approach that leverages large language models (LLMs) to construct personalized reasoning graphs.
Fine-grained Text and Image Guided Point Cloud Completion with CLIP Model
In this work, we propose a novel multimodal fusion network for point cloud completion, which can simultaneously fuse visual and textual information to predict the semantic and geometric characteristics of incomplete shapes effectively.
Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose Estimation
One critical challenge in 6D object pose estimation from a single RGBD image is efficient integration of two different modalities, i. e., color and depth.
Continual Learning in Predictive Autoscaling
In order to surmount this challenge and effectively integrate new sample distribution, we propose a density-based sample selection strategy that utilizes kernel density estimation to calculate sample density as a reference to compute sample weight, and employs weight sampling to construct a new memory set.
Federated Large Language Model: A Position Paper
Large scale language models (LLM) have received significant attention and found diverse applications across various domains, but their development encounters challenges in real-world scenarios.
Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
This paper presents ER-NeRF, a novel conditional Neural Radiance Fields (NeRF) based architecture for talking portrait synthesis that can concurrently achieve fast convergence, real-time rendering, and state-of-the-art performance with small model size.
EasyTPP: Towards Open Benchmarking Temporal Point Processes
In this paper, we present EasyTPP, the first central repository of research assets (e. g., data, models, evaluation programs, documentations) in the area of event sequence modeling.
Generative Contrastive Graph Learning for Recommendation
Second, feature augmentation imposes the same scale noise augmentation on each node, which neglects the unique characteristics of nodes on the graph.
InferTurbo: A Scalable System for Boosting Full-graph Inference of Graph Neural Network over Huge Graphs
Inspired by the philosophy of ``think-like-a-vertex", a GAS-like (Gather-Apply-Scatter) schema is proposed to describe the computation paradigm and data flow of GNN inference.
High Spectral Spatial Resolution Synthetic HyperSpectral Dataset form multi-source fusion
This research paper introduces a synthetic hyperspectral dataset that combines high spectral and spatial resolution imaging to achieve a comprehensive, accurate, and detailed representation of observed scenes or objects.
Deep Double Self-Expressive Subspace Clustering
The key idea of our solution is to view the self-expressive coefficient as a feature representation of the example to get another coefficient matrix.
RemoteCLIP: A Vision Language Foundation Model for Remote Sensing
However, these models primarily learn low-level features and require annotated data for fine-tuning.
Ranked #2 on
Cross-Modal Retrieval
on RSITMD
(using extra training data)
Description-Enhanced Label Embedding Contrastive Learning for Text Classification
Then, we propose a novel Relation of Relation Learning Network (R2-Net) for text classification, in which text classification and R2 classification are treated as optimization targets.
Dynamic Clustering Transformer Network for Point Cloud Segmentation
Specifically, we propose novel semantic feature-based dynamic sampling and clustering methods in the encoder, which enables the model to be aware of local semantic homogeneity for local feature aggregation.
Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning
Large language models have shown astonishing performance on a wide range of reasoning tasks.
ALT: An Automatic System for Long Tail Scenario Modeling
In this paper, we consider the problem of long tail scenario modeling with budget limitation, i. e., insufficient human resources for model training stage and limited time and computing resources for model inference stage.
Few-shot Classification via Ensemble Learning with Multi-Order Statistics
To address this need, we prove theoretically that leveraging ensemble learning on the base classes can correspondingly reduce the true error in the novel classes.
COUPA: An Industrial Recommender System for Online to Offline Service Platforms
Aiming at helping users locally discovery retail services (e. g., entertainment and dinning), Online to Offline (O2O) service platforms have become popular in recent years, which greatly challenge current recommender systems.
GARCIA: Powering Representations of Long-tail Query with Multi-granularity Contrastive Learning
At last, we conduct extensive experiments on both offline and online environments, which demonstrates the superior capability of GARCIA in improving tail queries and overall performance in service search scenarios.
Towards Open Temporal Graph Neural Networks
This will bring two big challenges to the existing dynamic GNN methods: (i) How to dynamically propagate appropriate information in an open temporal graph, where new class nodes are often linked to old class nodes.
Spectral 3D Computer Vision -- A Review
Spectral 3D computer vision examines both the geometric and spectral properties of objects.
Improving Recommendation Fairness via Data Augmentation
We augment imbalanced training data towards balanced data distribution to improve fairness.
DCMT: A Direct Entire-Space Causal Multi-Task Framework for Post-Click Conversion Estimation
In recommendation scenarios, there are two long-standing challenges, i. e., selection bias and data sparsity, which lead to a significant drop in prediction accuracy for both Click-Through Rate (CTR) and post-click Conversion Rate (CVR) tasks.
GCNet: Probing Self-Similarity Learning for Generalized Counting Network
The class-agnostic counting (CAC) problem has caught increasing attention recently due to its wide societal applications and arduous challenges.
The impact of access to credit on energy efficiency
This paper proposes a brand-new measure of energy efficiency at household level and explores how it is affected by access to credit.
Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift
From the perspective of invariant learning and stable learning, a recently well-established paradigm for out-of-distribution generalization, stable features of the graph are assumed to causally determine labels, while environmental features tend to be unstable and can lead to the two primary types of distribution shifts.
Robust Direct Learning for Causal Data Fusion
In the era of big data, the explosive growth of multi-source heterogeneous data offers many exciting challenges and opportunities for improving the inference of conditional average treatment effects.
Low Latency Conversion of Artificial Neural Network Models to Rate-encoded Spiking Neural Networks
The maximum number of spikes in this time window is also the latency of the network in performing a single inference, as well as determines the overall energy efficiency of the model.
PP-StructureV2: A Stronger Document Analysis System
For Table Recognition model, we utilize PP-LCNet, CSP-PAN and SLAHead to optimize the backbone module, feature fusion module and decoding module, respectively, which improved the table structure accuracy by 6\% with comparable inference speed.
Ranked #1 on
Network Pruning
on CIFAR-100
(Inference Time (ms) metric)
Label Inference Attacks Against Vertical Federated Learning
However, we discover that the bottom model structure and the gradient update mechanism of VFL can be exploited by a malicious participant to gain the power to infer the privately owned labels.
GraTO: Graph Neural Network Framework Tackling Over-smoothing with Neural Architecture Search
Further experiments bear out the quality of node representations learned with GraTO and the effectiveness of model architecture.
AHEAD: A Triple Attention Based Heterogeneous Graph Anomaly Detection Approach
In light of this problem, we propose AHEAD: a heterogeneity-aware unsupervised graph anomaly detection approach based on the encoder-decoder framework.
SO(3)-Pose: SO(3)-Equivariance Learning for 6D Object Pose Estimation
The SO(3)-equivariant features communicate with RGB features to deduce the (missed) geometry for detecting keypoints of an object with the reflective surface from the depth channel.
Ask Question First for Enhancing Lifelong Language Learning
Lifelong language learning aims to stream learning NLP tasks while retaining knowledge of previous tasks.
Gaia: Graph Neural Network with Temporal Shift aware Attention for Gross Merchandise Value Forecast in E-commerce
E-commerce has gone a long way in empowering merchants through the internet.
Agriculture-Vision Challenge 2022 -- The Runner-Up Solution for Agricultural Pattern Recognition via Transformer-based Models
The Agriculture-Vision Challenge in CVPR is one of the most famous and competitive challenges for global researchers to break the boundary between computer vision and agriculture sectors, aiming at agricultural pattern recognition from aerial images.
BadDet: Backdoor Attacks on Object Detection
We propose four kinds of backdoor attacks for object detection task: 1) Object Generation Attack: a trigger can falsely generate an object of the target class; 2) Regional Misclassification Attack: a trigger can change the prediction of a surrounding object to the target class; 3) Global Misclassification Attack: a single trigger can change the predictions of all objects in an image to the target class; and 4) Object Disappearance Attack: a trigger can make the detector fail to detect the object of the target class.
RVAE-LAMOL: Residual Variational Autoencoder to Enhance Lifelong Language Learning
In order to alleviate catastrophic forgetting, we propose the residual variational autoencoder (RVAE) to enhance LAMOL, a recent LLL model, by mapping different tasks into a limited unified semantic space.
KGNN: Distributed Framework for Graph Neural Knowledge Representation
Knowledge representation learning has been commonly adopted to incorporate knowledge graph (KG) into various online services.
Transfer Attacks Revisited: A Large-Scale Empirical Study in Real Computer Vision Settings
To bridge this critical gap, we conduct the first large-scale systematic empirical study of transfer attacks against major cloud-based MLaaS platforms, taking the components of a real transfer attack into account.
Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective
The stereo contrastive feature loss function explicitly constrains the consistency between learned features of matching pixel pairs which are observations of the same 3D points.
CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP
Existing state-of-the-art crowd counting algorithms rely excessively on location-level annotations, which are burdensome to acquire.
Neural Graph Matching for Pre-training Graph Neural Networks
In this way, we can learn adaptive representations for a given graph when paired with different graphs, and both node- and graph-level characteristics are naturally considered in a single pre-training task.
An Effective Graph Learning based Approach for Temporal Link Prediction: The First Place of WSDM Cup 2022
Temporal link prediction, as one of the most crucial work in temporal graphs, has attracted lots of attention from the research area.
Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift
To this end, in this paper, we propose a novel Distribution Recovered Graph Self-Training framework (DR-GST), which could recover the distribution of the original labeled dataset.
Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective
Our RGIB attempts to learn robust node representations against adversarial perturbations by preserving the original information in the benign graph while eliminating the adversarial information in the adversarial graph.
Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback
As a result, client sampling plays an important role in FL systems as it affects the convergence rate of optimization algorithms used to train machine learning models.
Benchmarking emergency department triage prediction models with machine learning and large public electronic health records
In this paper, based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we developed a publicly available benchmark suite for ED triage predictive models and created a benchmark dataset that contains over 400, 000 ED visits from 2011 to 2019.
Conditional Attention Networks for Distilling Knowledge Graphs in Recommendation
Knowledge graph is generally incorporated into recommender systems to improve overall performance.
MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data
Time series forecasting is widely used in business intelligence, e. g., forecast stock market price, sales, and help the analysis of data trend.
Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable
The Relation Extractor decomposes the complex question, and then the Reader answers the sub-questions in turn, and finally the Comparator performs numerical comparison and summarizes all to get the final answer, where the entire process itself constitutes a complete reasoning evidence path.
PPSGCN: A Privacy-Preserving Subgraph Sampling Based Distributed GCN Training Method
In light of these problems, we propose a Privacy-Preserving Subgraph sampling based distributed GCN training method (PPSGCN), which preserves data privacy and significantly cuts back on communication and memory overhead.
Reminding the Incremental Language Model via Data-Free Self-Distillation
Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks.
Improving Generative Adversarial Networks via Adversarial Learning in Latent Space
Although many efforts have been made in terms of backbone architecture design, loss function, and training techniques, few results have been obtained on how the sampling in latent space can affect the final performance, and existing works on latent space mainly focus on controllability.
PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System
Optical Character Recognition (OCR) systems have been widely used in various of application scenarios.
Optical Character Recognition
Optical Character Recognition (OCR)
A Unified Framework for Cross-Domain and Cross-System Recommendations
Moreover, to avoid negative transfer, we further propose a Personalized training strategy to minimize the embedding difference of common entities between a richer dataset and a sparser dataset, deriving three new models, i. e., GA-DTCDR-P, GA-MTCDR-P, and GA-CDR+CSR-P, for the three scenarios respectively.
SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendation
Specifically, we first encode user/item reviews via BERT and propose a light-weighted sentiment learner to extract semantic features of each review.
Improving Transferability of Adversarial Patches on Face Recognition with Generative Models
However, deep CNNs are vulnerable to adversarial patches, which are physically realizable and stealthy, raising new security concerns on the real-world applications of these models.
A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs
Combinatorial Optimization (CO) has been a long-standing challenging research topic featured by its NP-hard nature.
Improvement of Normal Estimation for PointClouds via Simplifying Surface Fitting
Firstly, a dynamic top-k selection strategy is introduced to better focus on the most critical points of a given patch, and the points selected by our learning method tend to fit a surface by way of a simple tangent plane, which can dramatically improve the normal estimation results of patches with sharp corners or complex patterns.
Fast and Accurate Normal Estimation for Point Cloud via Patch Stitching
At the stitching stage, we use the learned weights of multi-branch planar experts and distance weights between points to select the best normal from the overlapping parts.
Goal-Oriented Gaze Estimation for Zero-Shot Learning
Therefore, we introduce a novel goal-oriented gaze estimation module (GEM) to improve the discriminative attribute localization based on the class-level attributes for ZSL.
Cross-Domain Recommendation: Challenges, Progress, and Prospects
To address the long-standing data sparsity problem in recommender systems (RSs), cross-domain recommendation (CDR) has been proposed to leverage the relatively richer information from a richer domain to improve the recommendation performance in a sparser domain.
STNet: Scale Tree Network with Multi-level Auxiliator for Crowd Counting
To battle the ingrained issue of accuracy degradation, we propose a novel and powerful network called Scale Tree Network (STNet) for accurate crowd counting.
Towards Scalable and Privacy-Preserving Deep Neural Network via Algorithmic-Cryptographic Co-design
In this paper, we propose SPNN - a Scalable and Privacy-preserving deep Neural Network learning framework, from algorithmic-cryptographic co-perspective.
Multi-Interactive Attention Network for Fine-grained Feature Learning in CTR Prediction
In the Click-Through Rate (CTR) prediction scenario, user's sequential behaviors are well utilized to capture the user interest in the recent literature.
SMDS-Net: Model Guided Spectral-Spatial Network for Hyperspectral Image Denoising
This model first projects the observed HSIs into a low-dimensional orthogonal subspace, and then represents the projected image with a multidimensional dictionary.
ASFGNN: Automated Separated-Federated Graph Neural Network
Specifically, to solve the data Non-IID problem, we first propose a separated-federated GNN learning model, which decouples the training of GNN into two parts: the message passing part that is done by clients separately, and the loss computing part that is learnt by clients federally.
Multi-layer Feature Aggregation for Deep Scene Parsing Models
The proposed module can auto-select the intermediate visual features to correlate the spatial and semantic information.
Ranked #47 on
Semantic Segmentation
on NYU Depth v2
Parameter Efficient Deep Neural Networks with Bilinear Projections
Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy.
Synthetic MRI-aided Head-and-Neck Organs-at-Risk Auto-Delineation for CBCT-guided Adaptive Radiotherapy
The proposed method was evaluated on a cohort of 65 HN cancer patients.
Medical Physics Image and Video Processing
Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss
The proposed loss is generic and can be used as a plugin to replace the triplet loss to significantly enhance different types of state-of-the-art approaches.
PP-OCR: A Practical Ultra Lightweight OCR System
Meanwhile, several pre-trained models for the Chinese and English recognition are released, including a text detector (97K images are used), a direction classifier (600K images are used) as well as a text recognizer (17. 9M images are used).
Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning
Though many ZSL methods rely on a direct mapping between the visual and the semantic space, the calibration deviation and hubness problem limit the generalization capability to unseen classes.
3DPVNet: Patch-level 3D Hough Voting Network for 6D Pose Estimation
To address the problem, a novel 3DPVNet is presented in this work, which utilizes 3D local patches to vote for the object 6D poses.
A Comprehensive Analysis of Information Leakage in Deep Transfer Learning
To the best of our knowledge, our study is the first to provide a thorough analysis of the information leakage issues in deep transfer learning methods and provide potential solutions to the issue.
SAIL: Self-Augmented Graph Contrastive Learning
This paper studies learning node representations with graph neural networks (GNNs) for unsupervised scenario.
Heterogeneous Graph Neural Network for Recommendation
The prosperous development of e-commerce has spawned diverse recommendation systems.
When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Control
In this paper, we first present CAESAR, which combines HE and SS to build secure large-scale sparse logistic regression model and achieves both efficiency and security.
Bandit Samplers for Training Graph Neural Networks
However, due to the intractable computation of optimal sampling distribution, these sampling algorithms are suboptimal for GCNs and are not applicable to more general graph neural networks (GNNs) where the message aggregator contains learned weights rather than fixed weights, such as Graph Attention Networks (GAT).
Ranked #1 on
Node Property Prediction
on ogbn-proteins
Topological Hall Effect and Skyrmion-like Bubbles at a Charge-transfer Interface
Here, the emergence, tuning and interpretation of hump-shape Hall Effect from a CaMnO3/CaIrO3/CaMnO3 trilayer structure are studied in detail.
Mesoscale and Nanoscale Physics
Interlayer and Intralayer Scale Aggregation for Scale-invariant Crowd Counting
Crowd counting is an important vision task, which faces challenges on continuous scale variation within a given scene and huge density shift both within and across images.
Vertically Federated Graph Neural Network for Privacy-Preserving Node Classification
Recently, Graph Neural Network (GNN) has achieved remarkable progresses in various real-world tasks on graph data, consisting of node features and the adjacent information between different nodes.
Large-Scale Secure XGB for Vertical Federated Learning
Privacy-preserving machine learning has drawn increasingly attention recently, especially with kinds of privacy regulations come into force.
A Unified Weight Learning and Low-Rank Regression Model for Robust Complex Error Modeling
For the structured error caused by occlusions or disguises, we propose a GC function based rank approximation to measure the rank of error matrices.
Secret Sharing based Secure Regressions with Applications
Nowadays, the utilization of the ever expanding amount of data has made a huge impact on web technologies while also causing various types of security concerns.
Unpack Local Model Interpretation for GBDT
Besides the commonly used feature importance as a global interpretation, feature contribution is a local measure that reveals the relationship between a specific instance and the related output.
NetDP: An Industrial-Scale Distributed Network Representation Framework for Default Prediction in Ant Credit Pay
Considering the above challenges and the special scenario in Ant Financial, we try to incorporate default prediction with network information to alleviate the cold-start problem.
Privacy Preserving Point-of-interest Recommendation Using Decentralized Matrix Factorization
However, existing MF approaches suffer from two major problems: (1) Expensive computations and storages due to the centralized model training mechanism: the centralized learners have to maintain the whole user-item rating matrix, and potentially huge low rank matrices.
Industrial Scale Privacy Preserving Deep Neural Network
Deep Neural Network (DNN) has been showing great potential in kinds of real-world applications such as fraud detection and distress prediction.
RNE: A Scalable Network Embedding for Billion-scale Recommendation
However, due to the huge number of users and items, the diversity and dynamic property of the user interest, how to design a scalable recommendation system, which is able to efficiently produce effective and diverse recommendation results on billion-scale scenarios, is still a challenging and open problem for existing methods.
Generating Natural Language Adversarial Examples on a Large Scale with Generative Models
It can attack text classification models with a higher success rate than existing methods, and provide acceptable quality for humans in the meantime.
Practical Privacy Preserving POI Recommendation
Meanwhile, the public data need to be accessed by all the users are kept by the recommender to reduce the storage costs of users' devices.
InfDetect: a Large Scale Graph-based Fraud Detection System for E-Commerce Insurance
The insurance industry has been creating innovative products around the emerging online shopping activities.
SAFE: Scalable Automatic Feature Engineering Framework for Industrial Tasks
Machine learning techniques have been widely applied in Internet companies for various tasks, acting as an essential driving force, and feature engineering has been generally recognized as a crucial tache when constructing machine learning systems.
Data-Free Adversarial Perturbations for Practical Black-Box Attack
Adversarial examples often exhibit black-box attacking transferability, which allows that adversarial examples crafted for one model can fool another model.
A Semi-supervised Graph Attentive Network for Financial Fraud Detection
Additionally, among the network, only very few of the users are labelled, which also poses a great challenge for only utilizing labeled data to achieve a satisfied performance on fraud detection.
DSSLP: A Distributed Framework for Semi-supervised Link Prediction
Instead of training model on the whole graph, DSSLP is proposed to train on the \emph{$k$-hops neighborhood} of nodes in a mini-batch setting, which helps reduce the scale of the input graph and distribute the training procedure.
Uncovering Insurance Fraud Conspiracy with Network Learning
In order to detect and prevent fraudulent insurance claims, we developed a novel data-driven procedure to identify groups of organized fraudsters, one of the major contributions to financial losses, by learning network information.
Heterogeneous Graph Neural Networks for Malicious Account Detection
We present, GEM, the first heterogeneous graph neural network approach for detecting malicious accounts at Alipay, one of the world's leading mobile cashless payment platform.
How Much Can A Retailer Sell? Sales Forecasting on Tmall
By analyzing the data, we have two main observations, i. e., sales seasonality after we group different groups of retails and a Tweedie distribution after we transform the sales (target to forecast).
Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing
In this paper, we present a graph representation learning method atop of transaction networks for merchant incentive optimization in mobile payment marketing.
Deep Residual-Dense Lattice Network for Speech Enhancement
Motivated by this, we propose the residual-dense lattice network (RDL-Net), which is a new CNN for speech enhancement that employs both residual and dense aggregations without over-allocating parameters for feature re-usage.
Ranked #16 on
Speech Enhancement
on VoiceBank + DEMAND
Adapted tree boosting for Transfer Learning
Secure online transaction is an essential task for e-commerce platforms.
Secure Social Recommendation based on Secret Sharing
It is well known that social information, which is rich on social platforms such as Facebook, are useful to recommender systems.
Privacy Preserving PCA for Multiparty Modeling
In this paper, we present a general multiparty modeling paradigm with Privacy Preserving Principal Component Analysis (PPPCA) for horizontally partitioned data.
A Time Attention based Fraud Transaction Detection Framework
With online payment platforms being ubiquitous and important, fraud transaction detection has become the key for such platforms, to ensure user account safety and platform security.
Shenjing: A low power reconfigurable neuromorphic accelerator with partial-sum and spike networks-on-chip
We show that conventional artificial neural networks (ANN) such as multilayer perceptron, convolutional neural networks, as well as the latest residual neural networks can be mapped successfully onto Shenjing, realizing ANNs with SNN's energy efficiency.
Normal Estimation for 3D Point Clouds via Local Plane Constraint and Multi-scale Selection
Then we use multi-task optimization to train the normal estimation and local plane classification tasks simultaneously. Also, to integrate the advantages of multi-scale results, a scale selection strategy is adopted, which is a data-driven approach for selecting the optimal scale around each point and encourages subnetwork specialization.
Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics
Based on this framework, we demonstrate that SGLD can prevent the information leakage of the training dataset to a certain extent.
Pruning from Scratch
Network pruning is an important research field aiming at reducing computational costs of neural networks.
Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection
In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection.
A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks
Our method accelerates the network in one-step pruning-recovery manner with a novel optimization objective function, which achieves higher accuracy with much less cost compared with existing pruning methods.
TitAnt: Online Real-time Transaction Fraud Detection in Ant Financial
With the explosive growth of e-commerce and the booming of e-payment, detecting online transaction fraud in real time has become increasingly important to Fintech business.
Intrinsic Ferromagnetism in Electrenes
We report intrinsic ferromagnetism in monolayer electrides or electrenes, in which excess electrons act as anions.
Computational Physics Materials Science
Material Based Object Tracking in Hyperspectral Videos: Benchmark and Algorithms
Traditional color images only depict color intensities in red, green and blue channels, often making object trackers fail in challenging scenarios, e. g., background clutter and rapid changes of target appearance.
Object Tracking in Hyperspectral Videos with Convolutional Features and Kernelized Correlation Filter
Target tracking in hyperspectral videos is a new research topic.
Wearable Affective Robot
The learning algorithm for the life modeling embedded in Fitbot can achieve better user's experience of affective social interaction.
Electroencephalogram (EEG)
Human-Computer Interaction
Multi-scale Convolution Aggregation and Stochastic Feature Reuse for DenseNets
To address this problem, a regularization method named Stochastic Feature Reuse is also presented.
Semi-dense Stereo Matching using Dual CNNs
A robust solution for semi-dense stereo matching is presented.
Review Helpfulness Prediction with Embedding-Gated CNN
Product reviews, in the form of texts dominantly, significantly help consumers finalize their purchasing decisions.
Dropout with Tabu Strategy for Regularizing Deep Neural Networks
Tabu Dropout has no extra parameters compared with the standard Dropout and also it is computationally cheap.
Cross-Domain Review Helpfulness Prediction Based on Convolutional Neural Networks with Auxiliary Domain Discriminators
With the growing amount of reviews in e-commerce websites, it is critical to assess the helpfulness of reviews and recommend them accordingly to consumers.
Design Identification of Curve Patterns on Cultural Heritage Objects: Combining Template Matching and CNN-based Re-Ranking
The goal of this paper is to address the challenging problem of automatically identifying the underlying full design of curve patterns from such a sherd.
Distributed Deep Forest and its Application to Automatic Detection of Cash-out Fraud
This model can block fraud transactions in a large amount of money each day.
Feature Propagation on Graph: A New Perspective to Graph Representation Learning
In this paper, we first define the concept of feature propagation on graph formally, and then study its convergence conditions to equilibrium states.
A Boosting Framework of Factorization Machine
However, to choose the rank properly, it usually needs to run the algorithm for many times using different ranks, which clearly is inefficient for some large-scale datasets.
Distributed Collaborative Hashing and Its Applications in Ant Financial
The experimental results demonstrate that, comparing with the classic and state-of-the-art (distributed) latent factor models, DCH has comparable performance in terms of recommendation accuracy but has both fast convergence speed in offline model training procedure and realtime efficiency in online recommendation procedure.
Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression
In this way, most of the representative information in the network can be retained in each cluster.
Fast Subspace Clustering Based on the Kronecker Product
Therefore, the efficiency and scalability of traditional spectral clustering methods can not be guaranteed for large scale datasets.
Time-sensitive Customer Churn Prediction based on PU Learning
With the fast development of Internet companies throughout the world, customer churn has become a serious concern.
GeniePath: Graph Neural Networks with Adaptive Receptive Paths
We present, GeniePath, a scalable approach for learning adaptive receptive fields of neural networks defined on permutation invariant graph data.
Conditional Random Field and Deep Feature Learning for Hyperspectral Image Segmentation
Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing.
Curve-Structure Segmentation from Depth Maps: A CNN-based Approach and Its Application to Exploring Cultural Heritage Objects
Motivated by the important archaeological application of exploring cultural heritage objects, in this paper we study the challenging problem of automatically segmenting curve structures that are very weakly stamped or carved on an object surface in the form of a highly noisy depth map.
Clothing Retrieval with Visual Attention Model
The VAM is further connected to a global network to form an end-to-end network structure through Impdrop connection which randomly Dropout on the feature maps with the probabilities given by the attention map.
Small-footprint Keyword Spotting Using Deep Neural Network and Connectionist Temporal Classifier
Mainly for the sake of solving the lack of keyword-specific data, we propose one Keyword Spotting (KWS) system using Deep Neural Network (DNN) and Connectionist Temporal Classifier (CTC) on power-constrained small-footprint mobile devices, taking full advantage of general corpus from continuous speech recognition which is of great amount.
Attributing Hacks
That is, given properties of sites and the temporal occurrence of attacks, we are able to attribute individual attacks to joint causes and vulnerabilities, as well as estimating the evolution of these vulnerabilities over time.
Identifying Designs from Incomplete, Fragmented Cultural Heritage Objects by Curve-Pattern Matching
The challenge to reconstruct and study complete designs is stymied because 1) most fragmentary cultural-heritage objects contain only a small portion of the underlying full design, 2) in the case of a stamping application, the same design may be applied multiple times with spatial overlap on one object, and 3) curve patterns detected on an object are usually incomplete and noisy.
On the Sampling Strategy for Evaluation of Spectral-spatial Methods in Hyperspectral Image Classification
Spectral-spatial processing has been increasingly explored in remote sensing hyperspectral image classification.
