Search Results for author:
Found 140 papers, 46 papers with code
Social Bot-Aware Graph Neural Network for Early Rumor Detection
SBAG firstly pre-trains a multi-layer perception network to capture social bot features, and then constructs multiple graph neural networks by embedding the features to model the early propagation of posts, which is further used to detect rumors.
Diversity and Consistency: Exploring Visual Question-Answer Pair Generation
Moreover, this task can be used to improve visual question generation and visual question answering.
Improving Few-Shot Relation Classification by Prototypical Representation Learning with Definition Text
In this paper, we propose to learn a prototype encoder from relation definition in a way that is useful for relation instance classification.
PipeOptim: Ensuring Effective 1F1B Schedule with Optimizer-Dependent Weight Prediction
The key insight of our proposal is that we employ a weight prediction strategy in the forward pass to ensure that each mini-batch uses consistent and staleness-free weights to compute the forward pass.
TaskBench: Benchmarking Large Language Models for Task Automation
To this end, we introduce TaskBench to evaluate the capability of LLMs in task automation.
AdaMedGraph: Adaboosting Graph Neural Networks for Personalized Medicine
However, selecting the appropriate edge feature to define patient similarity and construct the graph is challenging, given that each patient is depicted by high-dimensional features from diverse sources.
Unified Medical Image Pre-training in Language-Guided Common Semantic Space
To overcome the aforementioned challenges, we propose an Unified Medical Image Pre-training framework, namely UniMedI, which utilizes diagnostic reports as common semantic space to create unified representations for diverse modalities of medical images (especially for 2D and 3D images).
TVT: Training-Free Vision Transformer Search on Tiny Datasets
In this paper, for the first time, we investigate how to search in a training-free manner with the help of teacher models and devise an effective Training-free ViT (TVT) search framework.
Online Video Quality Enhancement with Spatial-Temporal Look-up Tables
To the best of our knowledge, we are the first to exploit the LUT structure to extract temporal information in video tasks.
Towards Deeper, Lighter and Interpretable Cross Network for CTR Prediction
It is crucial to effectively model feature interactions to improve the prediction performance of CTR models.
Ranked #1 on
Click-Through Rate Prediction
on Criteo
A Comprehensive Summarization and Evaluation of Feature Refinement Modules for CTR Prediction
In addition, we present a new architecture of assigning independent FR modules to separate sub-networks for parallel CTR models, as opposed to the conventional method of inserting a shared FR module on top of the embedding layer.
Label Propagation for Graph Label Noise
In this paper, we study graph label noise in the context of arbitrary heterophily, with the aim of rectifying noisy labels and assigning labels to previously unlabeled nodes.
Rethinking SIGN Training: Provable Nonconvex Acceleration without First- and Second-Order Gradient Lipschitz
Sign-based stochastic methods have gained attention due to their ability to achieve robust performance despite using only the sign information for parameter updates.
Learning To Teach Large Language Models Logical Reasoning
Large language models (LLMs) have gained enormous attention from both academia and industry, due to their exceptional ability in language generation and extremely powerful generalization.
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
Inspired by these findings, we propose LongLLMLingua for prompt compression towards improving LLMs' perception of the key information to simultaneously address the three challenges.
GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence
Finally, we select the most fitting chains of evidence from the evidence forest and integrate them into the generated story, thereby enhancing the narrative's complexity and credibility.
RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents
The rapid evolution of the web has led to an exponential growth in content.
Towards Understanding the Generalizability of Delayed Stochastic Gradient Descent
Stochastic gradient descent (SGD) performed in an asynchronous manner plays a crucial role in training large-scale machine learning models.
AutoSeqRec: Autoencoder for Efficient Sequential Recommendation
Sequential recommendation demonstrates the capability to recommend items by modeling the sequential behavior of users.
DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptation
To this end, we employ domain adversarial learning as a heuristic neural network initialization method, which can help the meta-learning module converge to a better optimal.
Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classification
Theoretically, we prove the convergence of the meta-learning algorithm in MTEM and analyze the effectiveness of MTEM in achieving domain adaptation.
Recommendation Unlearning via Matrix Correction
We conducted comprehensive experiments to validate the effectiveness of IMCorrect and the results demonstrate that IMCorrect is superior in completeness, utility, and efficiency, and is applicable in many recommendation unlearning scenarios.
Seeing through the Brain: Image Reconstruction of Visual Perception from Human Brain Signals
Seeing is believing, however, the underlying mechanism of how human visual perceptions are intertwined with our cognitions is still a mystery.
A Dynamic Equivalent Method for PMSG Based Wind Farms Under Asymmetrical Faults
In this paper, a three-machine equivalent method applicable to asymmetrical faults is proposed considering the operating wind speed and fault severity.
Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance
Order execution is a fundamental task in quantitative finance, aiming at finishing acquisition or liquidation for a number of trading orders of the specific assets.
Large Language Models Empowered Autonomous Edge AI for Connected Intelligence
The evolution of wireless networks gravitates towards connected intelligence, a concept that envisions seamless interconnectivity among humans, objects, and intelligence in a hyper-connected cyber-physical world.
Is Risk-Sensitive Reinforcement Learning Properly Resolved?
Due to the nature of risk management in learning applicable policies, risk-sensitive reinforcement learning (RSRL) has been realized as an important direction.
Protecting the Future: Neonatal Seizure Detection with Spatial-Temporal Modeling
A timely detection of seizures for newborn infants with electroencephalogram (EEG) has been a common yet life-saving practice in the Neonatal Intensive Care Unit (NICU).
End-to-End Word-Level Pronunciation Assessment with MASK Pre-training
Pronunciation assessment is a major challenge in the computer-aided pronunciation training system, especially at the word (phoneme)-level.
XGrad: Boosting Gradient-Based Optimizers With Weight Prediction
the future weights to update the DNN parameters, making the gradient-based optimizer achieve better convergence and generalization compared to the original optimizer without weight prediction.
Simulating News Recommendation Ecosystem for Fun and Profit
In this work, we propose SimuLine, a simulation platform to dissect the evolution of news recommendation ecosystems and present a detailed analysis of the evolutionary process and underlying mechanisms.
DiffusionNER: Boundary Diffusion for Named Entity Recognition
In this paper, we propose DiffusionNER, which formulates the named entity recognition task as a boundary-denoising diffusion process and thus generates named entities from noisy spans.
Ranked #2 on
Nested Named Entity Recognition
on GENIA
Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks
However, most of the mixup methods do not consider the varying degree of learning difficulty in different stages of training and generate new samples with one hot labels, resulting in the model over confidence.
EA-HAS-Bench:Energy-Aware Hyperparameter and Architecture Search Benchmark
The energy consumption for training deep learning models is increasing at an alarming rate due to the growth of training data and model scale, resulting in a negative impact on carbon neutrality.
SIMPLE: Specialized Model-Sample Matching for Domain Generalization
Moreover, our method is highly efficient and achieves more than 1000 times training speedup compared to the conventional DG methods with fine-tuning a pretrained model.
Ranked #1 on
Domain Generalization
on PACS
MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks
In contrast, though human engineers have the incredible ability to understand tasks and reason about solutions, their experience and knowledge are often sparse and difficult to utilize by quantitative approaches.
Triple Structural Information Modelling for Accurate, Explainable and Interactive Recommendation
Specifically, TriSIM4Rec consists of 1) a dynamic ideal low-pass graph filter to dynamically mine co-occurrence information in user-item interactions, which is implemented by incremental singular value decomposition (SVD); 2) a parameter-free attention module to capture sequential information of user interactions effectively and efficiently; and 3) an item transition matrix to store the transition probabilities of item pairs.
Biological Factor Regulatory Neural Network
BFReg-NN starts from gene expression data and is capable of merging most existing biological knowledge into the model, including the regulatory relations among genes or proteins (e. g., gene regulatory networks (GRN), protein-protein interaction networks (PPI)) and the hierarchical relations among genes, proteins and pathways (e. g., several genes/proteins are contained in a pathway).
Habits and goals in synergy: a variational Bayesian framework for behavior
The habitual behavior is generated by using prior distribution of intention, which is goal-less; and the goal-directed behavior is generated by the posterior distribution of intention, which is conditioned on the goal.
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
Solving complicated AI tasks with different domains and modalities is a key step toward artificial general intelligence.
Leveraging Pretrained Representations with Task-related Keywords for Alzheimer's Disease Detection
This paper presents several efficient methods to extract better AD-related cues from high-level acoustic and linguistic features.
A Hierarchical Regression Chain Framework for Affective Vocal Burst Recognition
Experimental results based on the ACII Challenge 2022 dataset demonstrate the superior performance of the proposed system and the effectiveness of considering multiple relationships using hierarchical regression chain models.
Ranked #1 on
Vocal Bursts Intensity Prediction
on HUME-VB
Adaptive Policy Learning for Offline-to-Online Reinforcement Learning
In this paper, we consider an offline-to-online setting where the agent is first learned from the offline dataset and then trained online, and propose a framework called Adaptive Policy Learning for effectively taking advantage of offline and online data.
Rotation-Invariant Transformer for Point Cloud Matching
To this end, we introduce RoITr, a Rotation-Invariant Transformer to cope with the pose variations in the point cloud matching task.
Online Streaming Video Super-Resolution with Convolutional Look-Up Table
To facilitate the research on this problem, a new benchmark dataset named LDV-WebRTC is constructed based on a real-world online streaming system.
Unsupervised Video Anomaly Detection for Stereotypical Behaviours in Autism
Correspondingly, we propose a Dual Stream deep model for Stereotypical Behaviours Detection, DS-SBD, based on the temporal trajectory of human poses and the repetition patterns of human actions.
Personalized Graph Signal Processing for Collaborative Filtering
However, the interaction signal may not be sufficient to accurately characterize user interests and the low-pass filters may ignore the useful information contained in the high-frequency component of the observed signals, resulting in suboptimal accuracy.
Towards Inference Efficient Deep Ensemble Learning
Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e. g., can be up to 2048X in large-scale ensemble tasks.
SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking
In this paper, to comprehensively enhance the performance of generative graph SSL against other GCL models on both unsupervised and supervised learning tasks, we propose the SeeGera model, which is based on the family of self-supervised variational graph auto-encoder (VGAE).
Progressive Meta-Pooling Learning for Lightweight Image Classification Model
Practical networks for edge devices adopt shallow depth and small convolutional kernels to save memory and computational cost, which leads to a restricted receptive field.
RD-NAS: Enhancing One-shot Supernet Ranking Ability via Ranking Distillation from Zero-cost Proxies
In this paper, we propose Ranking Distillation one-shot NAS (RD-NAS) to enhance ranking consistency, which utilizes zero-cost proxies as the cheap teacher and adopts the margin ranking loss to distill the ranking knowledge.
OVO: One-shot Vision Transformer Search with Online distillation
OVO samples sub-nets for both teacher and student networks for better distillation results.
Learning Domain Invariant Prompt for Vision-Language Models
Prompt learning is one of the most effective and trending ways to adapt powerful vision-language foundation models like CLIP to downstream datasets by tuning learnable prompt vectors with very few samples.
SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems
In this paper, we propose a scalable evaluation methodology (SAIH) for analyzing the AI performance trend of HPC systems with scaling the problem sizes of customized AI applications.
CL4CTR: A Contrastive Learning Framework for CTR Prediction
Many Click-Through Rate (CTR) prediction works focused on designing advanced architectures to model complex feature interactions but neglected the importance of feature representation learning, e. g., adopting a plain embedding layer for each feature, which results in sub-optimal feature representations and thus inferior CTR prediction performance.
A Dynamic Equivalent Method for PMSG-WTG Based Wind Farms Considering wind Speeds and Fault Severities
In order to reduce the complexity of simulation of power systems including large-scale wind farms, it is critical to develop dynamic equivalent methods for wind farms which are applicable to the expected contingency analysis.
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification
Instead of learning fixed triggers for the target classes from the training set, DT-IBA can dynamically generate new triggers for any unknown identities.
Towards Understanding Omission in Dialogue Summarization
By analyzing this dataset, we find that a large improvement in summarization quality can be achieved by providing ground-truth omission labels for the summarization model to recover omission information, which demonstrates the importance of omission detection for omission mitigation in dialogue summarization.
Parameter-free Dynamic Graph Embedding for Link Prediction
Dynamic interaction graphs have been widely adopted to model the evolution of user-item interactions over time.
Reinforcement Learning with Automated Auxiliary Loss Search
A good state representation is crucial to solving complicated reinforcement learning (RL) challenges.
A Unified Generative Framework based on Prompt Learning for Various Information Extraction Tasks
In this paper, we propose a novel composable prompt-based generative framework, which could be applied to a wide range of tasks in the field of Information Extraction.
DMFormer: Closing the Gap Between CNN and Vision Transformers
Vision transformers have shown excellent performance in computer vision tasks.
Improving Hypernasality Estimation with Automatic Speech Recognition in Cleft Palate Speech
Specifically, we first pre-train an encoder-decoder framework in an automatic speech recognition (ASR) objective by using speech-to-text dataset, and then fine-tune ASR encoder on the cleft palate dataset for hypernasality estimation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Online Video Super-Resolution with Convolutional Kernel Bypass Graft
Then, our proposed CKBG method enhances this lightweight base model by bypassing the original network with ``kernel grafts'', which are extra convolutional kernels containing the prior knowledge of external pretrained image SR models.
Towards Privacy-Preserving Person Re-identification via Person Identify Shift
In this paper, we aim to develop a technique that can achieve a good trade-off between privacy protection and data usability for person ReID.
Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One
Autoregressive generative models are commonly used, especially for those tasks involving sequential data.
RendNet: Unified 2D/3D Recognizer With Latent Space Rendering
Instead of looking at one format, it is a good solution to utilize the formats of VG and RG together to avoid these shortcomings.
Bootstrapped Transformer for Offline Reinforcement Learning
Offline reinforcement learning (RL) aims at learning policies from previously collected static trajectory data without interacting with the real environment.
Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models
These features make it necessary to apply 3D parallelism, which integrates data parallelism, pipeline model parallelism and tensor model parallelism, to achieve high training efficiency.
Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling
Previous works on sentence scoring mainly adopted either causal language modeling (CLM) like GPT or masked language modeling (MLM) like BERT, which have some limitations: 1) CLM only utilizes unidirectional information for the probability estimation of a sentence without considering bidirectional context, which affects the scoring quality; 2) MLM can only estimate the probability of partial tokens at a time and thus requires multiple forward passes to estimate the probability of the whole sentence, which incurs large computation and time cost.
Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble
Considering the great performance of ensemble methods on both accuracy and generalization in supervised learning (SL), we design a robust and applicable method named Ensemble Proximal Policy Optimization (EPPO), which learns ensemble policies in an end-to-end manner.
Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
Further, for other homophilous nodes excluded in the neighborhood, they are ignored for information aggregation.
Ranked #1 on
Node Classification
on pokec
Enhancing CTR Prediction with Context-Aware Feature Representation Learning
However, most methods only learn a fixed representation for each feature without considering the varying importance of each feature under different contexts, resulting in inferior performance.
Learning Convolutional Neural Networks in the Frequency Domain
The most important motivation of this research is that we can use the straightforward element-wise multiplication operation to replace the image convolution in the frequency domain based on the Cross-Correlation Theorem, which obviously reduces the computation complexity.
Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation
Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time.
DELTA: Dynamically Optimizing GPU Memory beyond Tensor Recomputation
To the best of our knowledge, we are the first to make a reasonable dynamic runtime scheduler on the combination of tensor swapping and tensor recomputation without user oversight.
CMMD: Cross-Metric Multi-Dimensional Root Cause Analysis
To this end, we propose a cross-metric multi-dimensional root cause analysis method, named CMMD, which consists of two key components: 1) relationship modeling, which utilizes graph neural network (GNN) to model the unknown complex calculation among metrics and aggregation function among dimensions from historical data; 2) root cause localization, which adopts the genetic algorithm to efficiently and effectively dive into the raw data and localize the abnormal dimension(s) once the KPI anomalies are detected.
Domain Generalization using Pretrained Models without Fine-tuning
Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks.
Ranked #6 on
Domain Generalization
on PACS
Multi-trial Neural Architecture Search with Lottery Tickets
Neural architecture search (NAS) has brought significant progress in recent image recognition tasks.
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning
We propose VRL3, a powerful data-driven framework with a simple design for solving challenging visual deep reinforcement learning (DRL) tasks.
Neural Piecewise-Constant Delay Differential Equations
Continuous-depth neural networks, such as the Neural Ordinary Differential Equations (ODEs), have aroused a great deal of interest from the communities of machine learning and data science in recent years, which bridge the connection between deep neural networks and dynamical systems.
Reinforcement Learning Enhanced Explainer for Graph Neural Networks
To address these issues, we propose a RL-enhanced GNN explainer, RG-Explainer, which consists of three main components: starting point selection, iterative graph generation and stopping criteria learning.
Towards Generating Real-World Time Series Data
In this paper, we propose a novel generative framework for RTS data - RTSGAN to tackle the aforementioned challenges.
Recognizing Vector Graphics without Rasterization
In this paper, we consider a different data format for images: vector graphics.
EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks
EmbRace introduces Sparsity-aware Hybrid Communication, which integrates AlltoAll and model parallelism into data-parallel training, so as to reduce the communication overhead of highly sparse parameters.
Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
In this paper, to eliminate the effort for tuning the momentum-related hyperparameter, we propose a new adaptive momentum inspired by the optimal choice of the heavy ball momentum for quadratic optimization.
S2 Reducer: High-Performance Sparse Communication to Accelerate Distributed Deep Learning
Distributed stochastic gradient descent (SGD) approach has been widely used in large-scale deep learning, and the gradient collective method is vital to ensure the training scalability of the distributed deep learning system.
SANE: Specialization-Aware Neural Network Ensemble
Real-world data is often generated by some complex distribution, which can be approximated by a composition of multiple simpler distributions.
Deep Ensemble Policy Learning
Ensemble learning, which can consistently improve the prediction performance in supervised learning, has drawn increasing attentions in reinforcement learning (RL).
Variational oracle guiding for reinforcement learning
How to make intelligent decisions is a central problem in machine learning and cognitive science.
Adaptive Q-learning for Interaction-Limited Reinforcement Learning
Specifically, we explicitly consider the difference between the online and offline data and apply an adaptive update scheme accordingly, i. e., a pessimistic update strategy for the offline dataset and a greedy or no pessimistic update scheme for the online dataset.
AARL: Automated Auxiliary Loss for Reinforcement Learning
A good state representation is crucial to reinforcement learning (RL) while an ideal representation is hard to learn only with signals from the RL objective.
Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
The energy consumption of deep learning models is increasing at a breathtaking rate, which raises concerns due to potential negative effects on carbon neutrality in the context of global warming and climate change.
How Powerful is Graph Convolution for Recommendation?
In this paper, we endeavor to obtain a better understanding of GCN-based CF methods via the lens of graph signal processing.
Ranked #5 on
Collaborative Filtering
on Gowalla
Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
Confidence calibration is of great importance to the reliability of decisions made by machine learning systems.
Invariant Information Bottleneck for Domain Generalization
IIB significantly outperforms IRM on synthetic datasets, where the pseudo-invariant features and geometric skews occur, showing the effectiveness of proposed formulation in overcoming failure modes of IRM.
Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment
Based on the proposed quality measurement, we propose a deep Tiny Face Quality network (tinyFQnet) to learn a quality prediction function from data.
Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation
Hence, the key is to make full use of rich interaction information among streamers, users, and products.
Scalable and Explainable 1-Bit Matrix Completion via Graph Signal Learning
One-bit matrix completion is an important class of positiveunlabeled (PU) learning problems where the observations consist of only positive examples, eg, in top-N recommender systems.
Graph Pooling via Coarsened Graph Infomax
Graph pooling that summaries the information in a large graph into a compact form is essential in hierarchical graph representation learning.
Decentralized Federated Averaging
In FedAvg, clients keep their data locally for privacy protection; a central parameter server is used to communicate between clients.
NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering
In collaborative filtering (CF) algorithms, the optimal models are usually learned by globally minimizing the empirical risks averaged over all the observed data.
Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning
Graph neural networks (GNN) have been proven to be mature enough for handling graph-structured data on node-level graph representation learning tasks.
A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline
By monitoring the impact of varying resolution on the quality of high-dimensional video analytics features, hence the accuracy of video analytics results, the proposed end-to-end optimization framework learns the best non-myopic policy for dynamically controlling the resolution of input video streams to globally optimize energy efficiency.
Decentralized Statistical Inference with Unrolled Graph Neural Networks
In this paper, we investigate the decentralized statistical inference problem, where a network of agents cooperatively recover a (structured) vector from private noisy samples without centralized coordination.
Stability and Generalization of the Decentralized Stochastic Gradient Descent
The stability and generalization of stochastic gradient-based methods provide valuable insights into understanding the algorithmic performance of machine learning models.
Inertial Proximal Deep Learning Alternating Minimization for Efficient Neutral Network Training
In recent years, the Deep Learning Alternating Minimization (DLAM), which is actually the alternating minimization applied to the penalty form of the deep neutral networks training, has been developed as an alternative algorithm to overcome several drawbacks of Stochastic Gradient Descent (SGD) algorithms.
Learning content and context with language bias for Visual Question Answering
Many works concentrate on how to reduce language bias which makes models answer questions ignoring visual content and language context.
PPGN: Phrase-Guided Proposal Generation Network For Referring Expression Comprehension
Reference expression comprehension (REC) aims to find the location that the phrase refer to in a given image.
Meta-Learning for Neural Relation Classification with Distant Supervision
Distant supervision provides a means to create a large number of weakly labeled data at low cost for relation classification.
Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
First, we provide a finite sample bound for both classification and regression problems under Semi-DA.
Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning
In real world applications like healthcare, it is usually difficult to build a machine learning prediction model that works universally well across different institutions.
P-ADMMiRNN: Training RNN with Stable Convergence via An Efficient and Paralleled ADMM Approach
We also provide novel update rules and theoretical convergence analysis.
Adaptive Temporal Difference Learning with Linear Function Approximation
Typically, the performance of TD(0) and TD($\lambda$) is very sensitive to the choice of stepsizes.
Towards Precise End-to-end Weakly Supervised Object Detection Network
It is challenging for weakly supervised object detection network to precisely predict the positions of the objects, since there are no instance-level category annotations.
XPipe: Efficient Pipeline Model Parallelism for Multi-GPU DNN Training
It allows the overlapping of the pipelines of multiple micro-batches, including those belonging to different mini-batches.
General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme
In this paper, we propose a general proximal incremental aggregated gradient algorithm, which contains various existing algorithms including the basic incremental aggregated gradient method.
Decentralized Markov Chain Gradient Descent
Decentralized stochastic gradient method emerges as a promising solution for solving large-scale machine learning problems.
A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning
Rapid progress has been made in the field of reading comprehension and question answering, where several systems have achieved human parity in some simplified settings.
Ranked #8 on
Question Answering
on DROP Test
Heavy-ball Algorithms Always Escape Saddle Points
In this paper, we answer a question: can the nonconvex heavy-ball algorithms with random initialization avoid saddle points?
Exploring Pre-trained Language Models for Event Extraction and Generation
Traditional approaches to the task of ACE event extraction usually depend on manually annotated data, which is often laborious to create and limited in size.
Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension
This paper considers the reading comprehension task in which multiple documents are given as input.
Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification
Open-domain targeted sentiment analysis aims to detect opinion targets along with their sentiment polarities from a sentence.
Aspect-Based Sentiment Analysis (ABSA)
Aspect Term Extraction and Sentiment Classification
+1
Correlation Congruence for Knowledge Distillation
Most teacher-student frameworks based on knowledge distillation (KD) depend on a strong congruent constraint on instance level.
IF-TTN: Information Fused Temporal Transformation Network for Video Action Recognition
Focusing on discriminate spatiotemporal feature learning, we propose Information Fused Temporal Transformation Network (IF-TTN) for action recognition on top of popular Temporal Segment Network (TSN) framework.
Exploring Frame Segmentation Networks for Temporal Action Localization
The proposed FSN can make dense predictions at frame-level for a video clip using both spatial and temporal context information.
Iteratively reweighted penalty alternating minimization methods with continuation for image deblurring
In this paper, we consider a class of nonconvex problems with linear constraints appearing frequently in the area of image processing.
Collaborative Filtering with Stability
Collaborative filtering (CF) is a popular technique in today's recommender systems, and matrix approximation-based CF methods have achieved great success in both rating prediction and top-N recommendation tasks.
Non-ergodic Convergence Analysis of Heavy-Ball Algorithms
For objective functions satisfying a relaxed strongly convex condition, the linear convergence is established under weaker assumptions on the step size and inertial parameter than made in the existing literature.
An Efficient ADMM-Based Algorithm to Nonconvex Penalized Support Vector Machines
Support vector machines (SVMs) with sparsity-inducing nonconvex penalties have received considerable attentions for the characteristics of automatic classification and variable selection.
Attention-Guided Answer Distillation for Machine Reading Comprehension
Despite that current reading comprehension systems have achieved significant advancements, their promising performances are often obtained at the cost of making an ensemble of numerous models.
Read + Verify: Machine Reading Comprehension with Unanswerable Questions
Machine reading comprehension with unanswerable questions aims to abstain from answering when no answer can be inferred.
Ranked #11 on
Question Answering
on SQuAD2.0 dev
Loss Rank Mining: A General Hard Example Mining Method for Real-time Detectors
LRM is a general method for real-time detectors, as it utilizes the final feature map which exists in all real-time detectors to mine hard examples.
Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions
Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds.
Non-ergodic Complexity of Convex Proximal Inertial Gradient Descents
The non-ergodic O(1/k) rate is proved for proximal inertial gradient descent with constant stepzise when the objective function is coercive.
Mixture-Rank Matrix Approximation for Collaborative Filtering
However, our studies show that submatrices with different ranks could coexist in the same user-item rating matrix, so that approximations with fixed ranks cannot perfectly describe the internal structures of the rating matrix, therefore leading to inferior recommendation accuracy.
Ranked #4 on
Recommendation Systems
on MovieLens 10M
Exploring Temporal Preservation Networks for Precise Temporal Action Localization
A newly proposed work exploits Convolutional-Deconvolutional-Convolutional (CDC) filters to upsample the predictions of 3D ConvNets, making it possible to perform per-frame action predictions and achieving promising performance in terms of temporal action localization.
Open-Ended Question Answering
Temporal Action Localization
+1
S-OHEM: Stratified Online Hard Example Mining for Object Detection
S-OHEM exploits OHEM with stratified sampling, a widely-adopted sampling technique, to choose the training examples according to this influence during hard example mining, and thus enhance the performance of object detectors.
Weakly supervised object detection using pseudo-strong labels
Object detection is an import task of computer vision. A variety of methods have been proposed, but methods using the weak labels still do not have a satisfactory result. In this paper, we propose a new framework that using the weakly supervised method's output as the pseudo-strong labels to train a strongly supervised model. One weakly supervised method is treated as black-box to generate class-specific bounding boxes on train dataset. A de-noise method is then applied to the noisy bounding boxes. Then the de-noised pseudo-strong labels are used to train a strongly object detection network. The whole framework is still weakly supervised because the entire process only uses the image-level labels. The experiment results on PASCAL VOC 2007 prove the validity of our framework, and we get result 43. 4% on mean average precision compared to 39. 5% of the previous best result and 34. 5% of the initial method, respectively. And this frame work is simple and distinct, and is promising to be applied to other method easily.
