Search Results for author:
Found 86 papers, 37 papers with code
FS-Real: Towards Real-World Cross-Device Federated Learning
Federated Learning (FL) aims to train high-quality models in collaboration with distributed clients while not uploading their local data, which attracts increasing attention in both academia and industry.
VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation
A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data distribution.
Ranked #4 on
Video Generation
on UCF-101
ViM: Vision Middleware for Unified Downstream Transferring
ViM consists of a zoo of lightweight plug-in modules, each of which is independently learned on a midstream dataset with a shared frozen backbone.
Cones: Concept Neurons in Diffusion Models for Customized Generation
Concatenating multiple clusters of concept neurons can vividly generate all related concepts in a single image.
Meta-information-aware Dual-path Transformer for Differential Diagnosis of Multi-type Pancreatic Lesions in Multi-phase CT
Accurate detection, segmentation, and differential diagnosis of the full taxonomy of pancreatic lesions, i. e., normal, seven major types of lesions, and other lesions, is critical to aid the clinical decision-making of patient management and treatment.
Rethinking Efficient Tuning Methods from a Unified Perspective
The U-Tuning framework can simultaneously encompass existing methods and derive new approaches for parameter-efficient transfer learning, which prove to achieve on-par or better performances on CIFAR-100 and FGVC datasets when compared with existing PETL methods.
Composer: Creative and Controllable Image Synthesis with Composable Conditions
Recent large-scale generative models learned on big data are capable of synthesizing incredible images yet suffer from limited controllability.
Lero: A Learning-to-Rank Query Optimizer
In this paper, we introduce a learning-to-rank query optimizer, called Lero, which builds on top of a native query optimizer and continuously learns to improve the optimization performance.
Continual Segment: Towards a Single, Unified and Accessible Continual Segmentation Model of 143 Whole-body Organs in CT Scans
Deep learning empowers the mainstream medical image segmentation methods.
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
In contrast to predominant paradigms of solely relying on sequence-to-sequence generation or encoder-based instance discrimination, mPLUG-2 introduces a multi-module composition network by sharing common universal modules for modality collaboration and disentangling different modality modules to deal with modality entanglement.
Ranked #1 on
Visual Grounding
on RefCOCO+ testA
Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans
A certain number of AI models need to be assembled non-trivially to match the diagnostic process of a human reading a CT scan.
OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models
As a starting point, we provide presets of 7 different modalities and 23 highly-diverse example tasks in OFASys, with which we also develop a first-in-kind, single model, OFA+, that can handle text, image, speech, video, and motion data.
MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition
Therefore, we propose to introduce the phoneme modality into pre-training, which can help capture modality-invariant information between Mandarin speech and text.
Ranked #1 on
Speech Recognition
on AISHELL-1
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Dimensionality-Varying Diffusion Process
Diffusion models, which learn to reverse a signal destruction process to generate new data, typically require the signal at each step to have the same dimension.
Neural Dependencies Emerging from Learning Massive Categories
Through investigating the properties of the problem solution, we confirm that neural dependency is guaranteed by a redundant logit covariance matrix, which condition is easily met given massive categories, and that neural dependency is highly sparse, implying that one category correlates to only a few others.
Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
The tremendous success of CLIP (Radford et al., 2021) has promoted the research and application of contrastive learning for vision-language pretraining.
Ranked #1 on
Zero-shot Image Retrieval
on MUGE Retrieval
Device-Cloud Collaborative Recommendation via Meta Controller
To overcome this issue, we propose a meta controller to dynamically manage the collaboration between the on-device recommender and the cloud-based recommender, and introduce a novel efficient sample construction from the causal perspective to solve the dataset absence issue of meta controller.
Knowledge Distillation of Transformer-based Language Models Revisited
In the past few years, transformer-based pre-trained language models have achieved astounding success in both industry and academia.
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections
Large-scale pretrained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks.
Ranked #1 on
Image Captioning
on COCO Captions
Principled Knowledge Extrapolation with GANs
Human can extrapolate well, generalize daily knowledge into unseen scenarios, raise and answer counterfactual questions.
M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems
Industrial recommender systems have been growing increasingly complex, may involve \emph{diverse domains} such as e-commerce products and user-generated contents, and can comprise \emph{a myriad of tasks} such as retrieval, ranking, explanation generation, and even AI-assisted content production.
FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learning
The incredible development of federated learning (FL) has benefited various tasks in the domains of computer vision and natural language processing, and the existing frameworks such as TFF and FATE has made the deployment easy in real-world applications.
FederatedScope: A Flexible Federated Learning Platform for Heterogeneity
Although remarkable progress has been made by existing federated learning (FL) platforms to provide infrastructures for development, these platforms may not well tackle the challenges brought by various types of heterogeneity, including the heterogeneity in participants' local data, resources, behaviors and learning goals.
In-N-Out Generative Learning for Dense Unsupervised Video Segmentation
By contrast, pixel-level optimization is more explicit, however, it is sensitive to the visual quality of training data and is not robust to object deformation.
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization.
Ranked #1 on
Referring Expression Comprehension
on RefCoco+
(using extra training data)
Learning to be a Statistician: Learned Estimator for Number of Distinct Values
We derive conditions of the learning framework under which the learned model is workload agnostic, in the sense that the model/estimator can be trained with synthetically generated training data, and then deployed into any data warehouse simply as, e. g., user-defined functions (UDFs), to offer efficient (within microseconds on CPU) and accurate NDV estimations for unseen tables and workloads.
Baihe: SysML Framework for AI-driven Databases
Based on the high level architecture, we then describe a concrete implementation of Baihe for PostgreSQL and present example use cases for learned query optimizers.
Glue: Adaptively Merging Single Table Cardinality to Estimate Join Query Size
Cardinality estimation (CardEst), a central component of the query optimizer, plays a significant role in generating high-quality query plans in DBMS.
Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI
However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed.
M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining
Recent expeditious developments in deep learning algorithms, distributed training, and even hardware design for large models have enabled training extreme-scale models, say GPT-3 and Switch Transformer possessing hundreds of billions or even trillions of parameters.
iFlood: A Stable and Effective Regularizer
However, our further studies uncover that the design of the loss function of Flooding can lead to a discrepancy between its objective and implementation, and cause the instability issue.
Path-specific Causal Fair Prediction via Auxiliary Graph Structure Learning
To tackle these challenges, we propose a novel casual graph based fair prediction framework, which integrates graph structure learning into fair prediction to ensure that unfair pathways are excluded in the causal graph.
$\alpha$-Weighted Federated Adversarial Training
Federated Adversarial Training (FAT) helps us address the data privacy and governance issues, meanwhile maintains the model robustness to the adversarial attack.
Learned Index with Dynamic $\epsilon$
We theoretically analyze prediction error bounds that link $\epsilon$ with data characteristics for an illustrative learned index method.
Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation
Therefore, we propose a new metric P-Error to evaluate the performance of CardEst methods, which overcomes the limitation of Q-Error and is able to reflect the overall end-to-end performance of CardEst methods.
VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition
End-to-end AutoML has attracted intensive interests from both academia and industry, which automatically searches for ML pipelines in a space induced by feature engineering, algorithm/model selection, and hyper-parameter tuning.
Reliable Adversarial Distillation with Unreliable Teachers
However, when considering adversarial robustness, teachers may become unreliable and adversarial distillation may not work: teachers are pretrained on their own adversarial data, and it is too demanding to require that teachers are also good at every adversarial data queried by students.
Low-Rank Subspaces in GANs
Concretely, given an arbitrary image and a region of interest (e. g., eyes of face images), we manage to relate the latent space to the image region with the Jacobian matrix and then use low-rank factorization to discover steerable latent subspaces.
Learning to Rehearse in Long Sequence Memorization
Further, we design a history sampler to select informative fragments for rehearsal training, making the memory focus on the crucial information.
Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation
Experimental results demonstrate that our method outperforms the previous state-of-the-art methods in both automatic and human evaluation, especially on coverage and faithfulness.
M6-T: Exploring Sparse Expert Models and Beyond
Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scaling.
M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers
Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations.
Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention
With the rapid development of these services in the last two decades, users have accumulated a massive amount of behavior data.
Learning Relation Alignment for Calibrated Cross-modal Retrieval
To bridge the semantic gap between the two modalities, previous studies mainly focus on word-region alignment at the object level, lacking the matching between the linguistic relation among the words and the visual relation among the regions.
Ranked #3 on
Image-to-Text Retrieval
on COCO
Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation
Inspired by the idea of vector quantization that uses cluster centroids to approximate items, we propose LISA (LInear-time Self Attention), which enjoys both the effectiveness of vanilla self-attention and the efficiency of sparse attention.
UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis
Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations.
TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning
Secondly, on top of the proposed graph transformer, we introduce a two-stream encoder that separately extracts representations from temporal neighborhoods associated with the two interaction nodes and then utilizes a co-attentional transformer to model inter-dependencies at a semantic level.
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.
A Unified Transferable Model for ML-Enhanced DBMS
We propose to explore the transferabilities of the ML methods both across tasks and across DBs to tackle these fundamental drawbacks.
Device-Cloud Collaborative Learning for Recommendation
With the rapid development of storage and computing power on mobile devices, it becomes critical and popular to deploy models on devices to save onerous communication latencies and to capture real-time features.
M6: A Chinese Multimodal Pretrainer
In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1. 9TB images and 292GB texts that cover a wide range of domains.
Sparse-Interest Network for Sequential Recommendation
Our sparse-interest module can adaptively infer a sparse set of concepts for each user from the large concept pool and output multiple embeddings accordingly.
Dynamic Memory based Attention Network for Sequential Recommendation
It segments the overall long behavior sequence into a series of sub-sequences, then trains the model and maintains a set of memory blocks to preserve long-term interests of users.
Inductive Granger Causal Modeling for Multivariate Time Series
To bridge this gap, we propose an Inductive GRanger cAusal modeling (InGRA) framework for inductive Granger causality learning and common causal structure detection on multivariate time series, which exploits the shared commonalities underlying the different individuals.
FlashP: An Analytical Pipeline for Real-time Forecasting of Time-Series Relational Data
Our scalable real-time forecasting system FlashP (Flash Prediction) is built based on this idea, with two major challenges to be resolved in this paper: first, we need to figure out how approximate aggregations affect the fitting of forecasting models, and forecasting results; and second, accordingly, what sampling algorithms we should use to obtain these approximate aggregations and how large the samples are.
A Pluggable Learned Index Method via Sampling and Gap Insertion
In this paper, we propose a formal machine learning based framework to quantify the index learning objective, and study two general and pluggable techniques to enhance the learning efficiency and learning effectiveness for learned indexes.
Local Clustering Graph Neural Networks
Based on the theoretical analysis, we propose Local Clustering Graph Neural Networks (LCGNN), a GNN learning paradigm that utilizes local clustering to efficiently search for small but compact subgraphs for GNN training and inference.
Continual Memory: Can We Reason After Long-Term Memorization?
Existing reasoning tasks often follow the setting of "reasoning while experiencing", which has an important assumption that the raw contents can be always accessed while reasoning.
BayesCard: Revitilizing Bayesian Frameworks for Cardinality Estimation
Recently proposed deep learning based methods largely improve the estimation accuracy but their performance can be greatly affected by data and often difficult for system deployment.
Efficient and Scalable Structure Learning for Bayesian Networks: Algorithms and Applications
To resolve this, we propose a new structure learning algorithm LEAST, which comprehensively fulfills our business requirements as it attains high accuracy, efficiency and scalability at the same time.
Learning to Mutate with Hypergradient Guided Population
Computing the gradient of model hyperparameters, i. e., hypergradient, enables a promising and natural way to solve the hyperparameter optimization task.
FSPN: A New Class of Probabilistic Graphical Model
We introduce factorize sum split product networks (FSPNs), a new class of probabilistic graphical models (PGMs).
FLAT: Fast, Lightweight and Accurate Method for Cardinality Estimation
Despite decades of research, existing methods either over simplify the models only using independent factorization which leads to inaccurate estimates, or over complicate them by lossless conditional factorization without any independent assumption which results in slow probability computation.
MicroRec: Efficient Recommendation Inference by Hardware and Data Structure Solutions
MicroRec accelerates recommendation inference by (1) redesigning the data structures involved in the embeddings to reduce the number of lookups needed and (2) taking advantage of the availability of High-Bandwidth Memory (HBM) in FPGA accelerators to tackle the latency by enabling parallel lookups.
Poet: Product-oriented Video Captioner for E-commerce
Then, based on the aspects of the video-associated product, we perform knowledge-enhanced spatial-temporal inference on those graphs for capturing the dynamic change of fine-grained product-part characteristics.
FIVES: Feature Interaction Via Edge Search for Large-Scale Tabular Data
Then we instantiate this search strategy by optimizing both a dedicated graph neural network (GNN) and the adjacency tensor associated with the defined feature graph.
Comprehensive Information Integration Modeling Framework for Video Titling
In e-commerce, consumer-generated videos, which in general deliver consumers' individual preferences for the different aspects of certain products, are massive in volume.
Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems
Deep candidate generation (DCG) that narrows down the collection of relevant items from billions to hundreds via representation learning has become prevalent in industrial recommender systems.
Understanding Negative Sampling in Graph Representation Learning
To the best of our knowledge, we are the first to derive the theory and quantify that the negative sampling distribution should be positively but sub-linearly correlated to their positive sampling distribution.
Learning Efficient Parameter Server Synchronization Policies for Distributed SGD
We apply a reinforcement learning (RL) based approach to learning optimal synchronization policies used for Parameter Server-based distributed training of machine learning models with Stochastic Gradient Descent (SGD).
Taming the Expressiveness and Programmability of Graph Analytical Queries
Graph database has enjoyed a boom in the last decade, and graph queries accordingly gain a lot of attentions from both the academia and industry.
InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining
We pretrain the model with three pretraining tasks, including masked segment modeling (MSM), masked region modeling (MRM) and image-text matching (ITM); and finetune the model on a series of vision-and-language downstream tasks.
Learning to Hash with Graph Neural Networks for Recommender Systems
In this work, we investigate the problem of hashing with graph neural networks (GNNs) for high quality retrieval, and propose a simple yet effective discrete representation learning framework to jointly learn continuous and discrete codes.
AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search
Motivated by the necessity and benefits of task-oriented BERT compression, we propose a novel compression method, AdaBERT, that leverages differentiable Neural Architecture Search to automatically compress BERT into task-adaptive small models for specific tasks.
Granger Causal Structure Reconstruction from Heterogeneous Multivariate Time Series
Granger causal structure reconstruction is an emerging topic that can uncover causal relationship behind multivariate time series data.
Improving Utility and Security of the Shuffler-based Differential Privacy
When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the central aggregator.
Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks
Low-dimensional embeddings of knowledge graphs and behavior graphs have proved remarkably powerful in varieties of tasks, from predicting unobserved edges between entities to content recommendation.
A Minimax Game for Instance based Selective Transfer Learning
To the best of our knowledge, this is the first to build a minimax game based model for selective transfer learning.
A Survey and Experimental Analysis of Distributed Subgraph Matching
We conduct extensive experiments for both unlabelled matching and labelled matching to analyze the performance of distributed subgraph matching under various settings, which is finally summarized as a practical guide.
Databases
Sequential Scenario-Specific Meta Learner for Online Recommendation
Our approach is based on the insight that having a good generalization from a few examples relies on both a generic model initialization and an effective strategy for adapting this model to newly arising tasks.
Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding
Network embedding models are powerful tools in mapping nodes in a network into continuous vector-space representations in order to facilitate subsequent tasks such as classification and link prediction.
Representation Learning for Attributed Multiplex Heterogeneous Network
Network embedding (or graph embedding) has been widely used in many real-world applications.
Ranked #1 on
Link Prediction
on Amazon
Towards Knowledge-Based Personalized Product Description Generation in E-commerce
In order to make the description both informative and personalized, KOBE considers a variety of important factors during text generation, including product aspects, user categories, and knowledge base, etc.
AliGraph: A Comprehensive Graph Neural Network Platform
An increasing number of machine learning tasks require dealing with large graph datasets, which capture rich and complex relationship among potentially billions of elements.
Distributed, Parallel, and Cluster Computing
PANDA: Facilitating Usable AI Development
In many complex applications such as healthcare, subject matter experts (e. g. Clinicians) are the ones who appreciate the importance of features that affect health, and their knowledge together with existing knowledge bases are critical to the end results.
Large-scale L-BFGS using MapReduce
L-BFGS has been applied as an effective parameter estimation method for various machine learning algorithms since 1980s.
