Search Results for author:
Found 370 papers, 147 papers with code
Unified Language Model Pre-training for Natural Language Understanding and Generation
This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks.
Ranked #2 on
Generative Question Answering
on CoQA
(using extra training data)
UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM).
Ranked #4 on
Question Generation
on SQuAD1.1
(using extra training data)
Pseudo-Masked Language Models for Unified Language Model Pre-Training
We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM).
Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling
In this paper, we focus on the compression of DETR with knowledge distillation.
SQLFlow: A Bridge between SQL and Machine Learning
Previous database systems extended their SQL dialect to support ML.
LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
Ranked #29 on
Real-Time Semantic Segmentation
on Cityscapes test
ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation
The whole network has nearly symmetric architecture, which is mainly composed of a series of factorized convolution unit (FCU) and its parallel counterparts (PFCU).
Ranked #28 on
Real-Time Semantic Segmentation
on Cityscapes test
The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games
This is often due to the belief that PPO is significantly less sample efficient than off-policy methods in multi-agent systems.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding
We present MT-DNN, an open-source natural language understanding (NLU) toolkit that makes it easy for researchers and developers to train customized deep learning models.
Adversarial Training for Large Neural Language Models
In natural language processing (NLP), pre-training large neural language models such as BERT have demonstrated impressive gain in generalization for a variety of tasks, with further improvement from adversarial fine-tuning.
Ranked #6 on
Natural Language Inference
on ANLI test
(using extra training data)
GE-SpMM: General-purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networks
GE-SpMM performs SpMM-like operation on sparse matrices represented in the most common Compressed Sparse Row (CSR) format, so it can be embedded in GNN frameworks with no preprocessing overheads and support general GNN algorithms.
Distributed, Parallel, and Cluster Computing
CogDL: A Comprehensive Library for Graph Deep Learning
In CogDL, we propose a unified design for the training and evaluation of GNN models for various graph tasks, making it unique among existing graph learning libraries.
DNNVM : End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-based CNN Accelerators
On the Xilinx ZU2 @330 MHz and ZU9 @330 MHz, we achieve equivalently state-of-the-art performance on our benchmarks by na\"ive implementations without optimizations, and the throughput is further improved up to 1. 26x by leveraging heterogeneous optimizations in DNNVM.
TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs
On top of this, we design the Sparse Autotuner, which extends the design space of existing sparse convolution libraries and searches for the best dataflow configurations for training and inference workloads.
ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing
Here, we trained two auto-regressive models (Transformer-XL, XLNet) and four auto-encoder models (BERT, Albert, Electra, T5) on data from UniRef and BFD containing up to 393 billion amino acids.
Ranked #1 on
Protein Secondary Structure Prediction
on CASP12
Dimensionality Reduction
Protein Secondary Structure Prediction
ChemicalX: A Deep Learning Library for Drug Pair Scoring
In this paper, we introduce ChemicalX, a PyTorch-based deep learning library designed for providing a range of state of the art models to solve the drug pair scoring task.
Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator
Large Language Models (LLMs) have demonstrated remarkable proficiency in human interactions, yet their application within the medical field remains insufficiently explored.
MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts
Large language models like ChatGPT have shown substantial progress in natural language understanding and generation, proving valuable across various disciplines, including the medical field.
Track to Detect and Segment: An Online Multi-Object Tracker
Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking.
Ranked #1 on
Instance Segmentation
on nuScenes
Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions.
Ranked #7 on
Long-tail Learning
on VOC-MLT
CenterFormer: Center-based Transformer for 3D Object Detection
It then uses the feature of the center candidate as the query embedding in the transformer.
Ranked #2 on
3D Object Detection
on waymo cyclist
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
The situation gets even worse with distributed training on mobile devices (federated learning), which suffers from higher latency, lower throughput, and intermittent poor connections.
A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS
Experimental results on various search spaces confirm GATES's effectiveness in improving the performance predictor.
Evaluating Efficient Performance Estimators of Neural Architectures
Conducting efficient performance estimations of neural architectures is a major challenge in neural architecture search (NAS).
aw_nas: A Modularized and Extensible NAS framework
Neural Architecture Search (NAS) has received extensive attention due to its capability to discover neural network architectures in an automated manner.
Discovering Robust Convolutional Architecture at Targeted Capacity: A Multi-Shot Approach
In this paper, considering scenarios with capacity budget, we aim to discover adversarially robust architecture at targeted capacities.
CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS
Specifically, we train the supernet with a large sharing extent (an easier curriculum) at the beginning and gradually decrease the sharing extent of the supernet (a harder curriculum).
Curating a COVID-19 data repository and forecasting county-level death counts in the United States
We use this data to develop predictions and corresponding prediction intervals for the short-term trajectory of COVID-19 cumulative death counts at the county-level in the United States up to two weeks ahead.
Deep Gradient Compression Reduce the Communication Bandwidth For distributed Traning
Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure.
Microsoft Dialogue Challenge: Building End-to-End Task-Completion Dialogue Systems
This proposal introduces a Dialogue Challenge for building end-to-end task-completion dialogue systems, with the goal of encouraging the dialogue research community to collaborate and benchmark on standard datasets and unified experimental environment.
EVI-SAM: Robust, Real-time, Tightly-coupled Event-Visual-Inertial State Estimation and 3D Dense Mapping
To the best of our knowledge, this is the first non-learning work to realize event-based dense mapping.
Knowledge Graph Prompting for Multi-Document Question Answering
Concurrently, the graph traversal agent acts as a local navigator that gathers pertinent context to progressively approach the question and guarantee retrieval quality.
AFDet: Anchor Free One Stage 3D Object Detection
High-efficiency point cloud 3D object detection operated on embedded systems is important for many robotics applications including autonomous driving.
Dual Vision Transformer
Dual-ViT is henceforth able to reduce the computational complexity without compromising much accuracy.
Improving Out-of-Distribution Robustness via Selective Augmentation
Machine learning algorithms typically assume that training and test examples are drawn from the same distribution.
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
This work aims at decreasing the end-to-end generation latency of large language models (LLMs).
OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control
In this work, we introduce OmniDrones, an efficient and flexible platform tailored for reinforcement learning in drone control, built on Nvidia's Omniverse Isaac Sim.
Adversarial Robustness under Long-Tailed Distribution
We then perform a systematic study on existing long-tailed recognition methods in conjunction with the adversarial training framework.
BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs
Therefore, training an effective generalist biomedical model requires high-quality multimodal data, such as parallel image-text pairs.
Ranked #3 on
Medical Visual Question Answering
on SLAKE-English
Large Trajectory Models are Scalable Motion Predictors and Planners
STR reformulates the motion prediction and motion planning problems by arranging observations, states, and actions into one unified sequence modeling task.
Learning a Unified Sample Weighting Network for Object Detection
To this end, we devise a general loss function to cover most region-based object detectors with various sampling strategies, and then based on it we propose a unified sample weighting network to predict a sample's task weights.
Efficient Context-Aware Network for Abdominal Multi-organ Segmentation
For the context block, we propose strip pooling module to capture anisotropic and long-range contextual information, which exists in abdominal scene.
Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation
Our models outperform other SSL models significantly on the LibriSpeech benchmark without the need for iterative re-clustering and re-training.
Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently.
Ranked #34 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Evaluating Quantized Large Language Models
Post-training quantization (PTQ) has emerged as a promising technique to reduce the cost of large language models (LLMs).
Multi-view Deep Subspace Clustering Networks
Dnet learns view-specific self-representation matrices, whereas Unet learns a common self-representation matrix for all views.
Ranked #1 on
Multi-view Subspace Clustering
on ORL
ExKaldi-RT: A Real-Time Automatic Speech Recognition Extension Toolkit of Kaldi
This paper describes the ExKaldi-RT online automatic speech recognition (ASR) toolkit that is implemented based on the Kaldi ASR toolkit and Python language.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
MechRetro is a chemical-mechanism-driven graph learning framework for interpretable retrosynthesis prediction and pathway planning
Leveraging artificial intelligence for automatic retrosynthesis speeds up organic pathway planning in digital laboratories.
Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer
We firstly pre-train a transformer with sequences in a reverse direction to predict prior items.
Collaboration-Aware Graph Convolutional Network for Recommender Systems
Graph Neural Networks (GNNs) have been successfully adopted in recommender systems by virtue of the message-passing that implicitly captures collaborative effect.
Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction
Aspect sentiment triplet extraction (ASTE), which aims to identify aspects from review sentences along with their corresponding opinion expressions and sentiments, is an emerging task in fine-grained opinion mining.
Aspect Sentiment Triplet Extraction
Machine Reading Comprehension
+2
Imbalanced Graph Classification via Graph-of-Graph Neural Networks
To this end, we introduce a novel framework, Graph-of-Graph Neural Networks (G$^2$GNN), which alleviates the graph imbalance issue by deriving extra supervision globally from neighboring graphs and locally from stochastic augmentations of graphs.
Joint Contrastive Learning with Infinite Possibilities
This paper explores useful modifications of the recent development in contrastive learning via novel probabilistic modeling.
Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization
We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games.
Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis
Though Multimodal Sentiment Analysis (MSA) proves effective by utilizing rich information from multiple sources (e. g., language, video, and audio), the potential sentiment-irrelevant and conflicting information across modalities may hinder the performance from being further improved.
Ranked #1 on
Multimodal Sentiment Analysis
on CMU-MOSEI
(Acc-7 metric)
Machine Learning for Electronic Design Automation: A Survey
With the down-scaling of CMOS technology, the design complexity of very large-scale integrated (VLSI) is increasing.
A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling
The most effective algorithms are based on the structures of sequence to sequence models (or "encoder-decoder" models), and generate the intents and semantic tags either using separate models or a joint model.
Ranked #1 on
Intent Detection
on ATIS
Learn from Each Other to Classify Better: Cross-layer Mutual Attention Learning for Fine-grained Visual Classification
Specifically, this work views the shallow to deep layers of CNNs as “experts” knowledgeable about different perspectives.
Ranked #1 on
Fine-Grained Image Classification
on Stanford Cars
(using extra training data)
A Neural Transition-based Model for Nested Mention Recognition
It is common that entity mentions can contain other mentions recursively.
Ranked #6 on
Nested Named Entity Recognition
on NNE
Nested Mention Recognition
Nested Named Entity Recognition
+1
Few-Shot Specific Emitter Identification via Deep Metric Ensemble Learning
Thus, we focus on few-shot SEI (FS-SEI) for aircraft identification via automatic dependent surveillance-broadcast (ADS-B) signals, and a novel FS-SEI method is proposed, based on deep metric ensemble learning (DMEL).
Distance-wise Prototypical Graph Neural Network in Node Imbalance Classification
Recent years have witnessed the significant success of applying graph neural networks (GNNs) in learning effective node representations for classification.
ContrastVAE: Contrastive Variational AutoEncoder for Sequential Recommendation
Then we propose Contrastive Variational AutoEncoder (ContrastVAE in short), a two-branched VAE model with contrastive regularization as an embodiment of ContrastELBO for sequential recommendation.
Learning Concise and Descriptive Attributes for Visual Recognition
Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language models to classify images via these attributes.
LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models
While Large Language Models (LLMs) have demonstrated commendable performance across a myriad of domains and tasks, existing LLMs still exhibit a palpable deficit in handling multimodal functionalities, especially for the Spoken Question Answering (SQA) task which necessitates precise alignment and deep interaction between speech and text features.
Synchronous Double-channel Recurrent Network for Aspect-Opinion Pair Extraction
The opinion entity extraction unit and the relation detection unit are developed as two channels to extract opinion entities and relations simultaneously.
Learning to Adapt to Evolving Domains
(2) Since the target data arrive online, the agent should also maintain competence on previous target domains, i. e. to adapt without forgetting.
Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
A crucial limitation of this framework is that every policy in the pool is optimized w. r. t.
Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation
Recent leading zero-shot video object segmentation (ZVOS) works devote to integrating appearance and motion information by elaborately designing feature fusion modules and identically applying them in multiple feature stages.
Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage
Motivated by our analysis, we propose Fair View Graph Neural Network (FairVGNN) to generate fair views of features by automatically identifying and masking sensitive-correlated features considering correlation variation after feature propagation.
PiCO: Peer Review in LLMs based on the Consistency Optimization
Existing large language models (LLMs) evaluation methods typically focus on testing the performance on some closed-environment and domain-specific benchmarks with human annotations.
LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K
In contrast, the average context lengths of mainstream benchmarks are insufficient (5k-21k), and they suffer from potential knowledge leakage and inaccurate metrics, resulting in biased evaluation.
Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning
We present a reinforcement learning (RL) framework to synthesize a control policy from a given linear temporal logic (LTL) specification in an unknown stochastic environment that can be modeled as a Markov Decision Process (MDP).
Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation
Furthermore, we propose a Federated learning paradigm with privacy-preserving Relation embedding aggregation (FedR) to tackle the privacy issue in FedE.
AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting
However, with the integration of additional modalities, MLLMs are exposed to new vulnerabilities, rendering them prone to structured-based jailbreak attacks, where semantic content (e. g., "harmful text") has been injected into the images to mislead MLLMs.
ParCo: Part-Coordinating Text-to-Motion Synthesis
However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts.
Ranked #8 on
Motion Synthesis
on HumanML3D
Face Hallucination via Split-Attention in Split-Attention Network
However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e. g., face detection, facial recognition).
DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN
In the information explosion era, recommender systems (RSs) are widely studied and applied to discover user-preferred information.
Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning
We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field.
Tree Decomposed Graph Neural Network
Nevertheless, iterative propagation restricts the information of higher-layer neighborhoods to be transported through and fused with the lower-layer neighborhoods', which unavoidably results in feature smoothing between neighborhoods in different layers and can thus compromise the performance, especially on heterophily networks.
Ranked #25 on
Node Classification
on Cora
OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
Diffusion probabilistic models (DPMs) are a new class of generative models that have achieved state-of-the-art generation quality in various domains.
Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems
We motivate our paradigm through a variational perspective, where the learning objective can be decomposed into two terms: task learning on the current task distribution, and curriculum update to a new task distribution.
A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications
Despite this progress, there is a lack of a comprehensive overview of the attacks and the techniques for preserving privacy in the graph domain.
Meta-learning with an Adaptive Task Scheduler
In ATS, for the first time, we design a neural scheduler to decide which meta-training tasks to use next by predicting the probability being sampled for each candidate task, and train the scheduler to optimize the generalization capacity of the meta-model to unseen tasks.
Unsupervised Remote Sensing Super-Resolution via Migration Image Prior
Despite their success, however, low/high spatial resolution pairs are usually difficult to obtain in satellites with a high temporal resolution, making such approaches in SR impractical to use.
Contribution of Radio Halos to the Foreground for SKA EoR Experiments
The overwhelming foreground contamination is one of the primary impediments to probing the EoR through measuring the redshifted 21 cm signal.
Cosmology and Nongalactic Astrophysics
Ultra Lite Convolutional Neural Network for Fast Automatic Modulation Classification in Low-Resource Scenarios
Automatic modulation classification (AMC) is a key technique for designing non-cooperative communication systems, and deep learning (DL) is applied effectively to AMC for improving classification accuracy.
DeSCo: Towards Generalizable and Scalable Deep Subgraph Counting
We introduce DeSCo, a scalable neural deep subgraph counting pipeline, designed to accurately predict both the count and occurrence position of queries on target graphs post single training.
Large-scale Personalized Video Game Recommendation via Social-aware Contextualized Graph Neural Network
We conduct a comprehensive analysis of users' online game behaviors, which motivates the necessity of handling those three characteristics in the online game recommendation.
LINFA: a Python library for variational inference with normalizing flow and annealing
Variational inference is an increasingly popular method in statistics and machine learning for approximating probability distributions.
Halo: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language Models
Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP).
A Debiased MDI Feature Importance Measure for Random Forests
Based on the original definition of MDI by Breiman et al. for a single tree, we derive a tight non-asymptotic bound on the expected bias of MDI importance of noisy features, showing that deep trees have higher (expected) feature selection bias than shallow ones.
GypSum: Learning Hybrid Representations for Code Summarization
Current deep learning models for code summarization generally follow the principle in neural machine translation and adopt the encoder-decoder framework, where the encoder learns the semantic representations from source code and the decoder transforms the learnt representations into human-readable text that describes the functionality of code snippets.
LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination
AI agents powered by Large Language Models (LLMs) have made significant advances, enabling them to assist humans in diverse complex tasks and leading to a revolution in human-AI coordination.
Steklov Spectral Geometry for Extrinsic Shape Analysis
We propose using the Dirichlet-to-Neumann operator as an extrinsic alternative to the Laplacian for spectral geometry processing and shape analysis.
Graphics
SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement
In this paper, we propose a novel deep architecture tailored for 3D point cloud applications, named as SPE-Net.
Exploring Diverse Representations for Open Set Recognition
We show that the differences in attention maps can lead to diverse representations so that the fused representations can well handle the open space.
PepLand: a large-scale pre-trained peptide representation model for a comprehensive landscape of both canonical and non-canonical amino acids
In recent years, the scientific community has become increasingly interested on peptides with non-canonical amino acids due to their superior stability and resistance to proteolytic degradation.
Learning a Static Bug Finder from Data
In a cross-project prediction task, three neural bug detectors we instantiate from NeurSA are effective in catching null pointer dereference, array index out of bound and class cast bugs in unseen code.
LVCHAT: Facilitating Long Video Comprehension
To address this issue, we propose Long Video Chat (LVChat), where Frame-Scalable Encoding (FSE) is introduced to dynamically adjust the number of embeddings in alignment with the duration of the video to ensure long videos are not overly compressed into a few embeddings.
DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation
In budgeted pruning, how to distribute the resources across layers (i. e., sparsity allocation) is the key problem.
BoolNet: Minimizing The Energy Consumption of Binary Neural Networks
Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts.
Out-of-Distribution Detection with Hilbert-Schmidt Independence Optimization
Existing works attempt to solve the problem by explicitly imposing uncertainty on classifiers when OOD inputs are exposed to the classifier during training.
Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration
Simply waiting for every robot being ready for the next action can be particularly time-inefficient.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Binding-Adaptive Diffusion Models for Structure-Based Drug Design
Then the selected protein-ligand subcomplex is processed with SE(3)-equivariant neural networks, and transmitted back to each atom of the complex for augmenting the target-aware 3D molecule diffusion generation with binding interaction information.
On Structural Explanation of Bias in Graph Neural Networks
The low transparency on how the structure of the input network influences the bias in GNN outcome largely limits the safe adoption of GNNs in various decision-critical scenarios.
Relational Prior Knowledge Graphs for Detection and Instance Segmentation
Humans have a remarkable ability to perceive and reason about the world around them by understanding the relationships between objects.
Introducing π-HelixNovo for practical large-scale de novo peptide sequencing
De novo peptide sequencing is a promising approach for novel peptide discovery.
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
For example, LCSC achieves better performance using 1 number of function evaluation (NFE) than the base model with 2 NFE on consistency distillation, and decreases the NFE of DM from 15 to 9 while maintaining the generation quality on CIFAR-10.
Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration
Our work reveals a structured shortcoming of the existing mainstream self-supervised learning methods.
Fairness and Explainability: Bridging the Gap Towards Fair Model Explanations
Although research efforts have been devoted to measuring and mitigating bias, they mainly study bias from the result-oriented perspective while neglecting the bias encoded in the decision-making procedure.
Toward Extremely Lightweight Distracted Driver Recognition With Distillation-Based Neural Architecture Search and Knowledge Transfer
Experimental results on the Statefarm Distracted Driver Detection Dataset and AUC Distracted Driver Dataset show that the proposed approach is highly effective for recognizing distracted driving behaviors from photos: (1) the teacher network's accuracy surpasses the previous best accuracy; (2) the student network achieves very high accuracy with only 0. 42M parameters (around 55% of the previous most lightweight model).
Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation
Most existing online knowledge distillation(OKD) techniques typically require sophisticated modules to produce diverse knowledge for improving students' generalization ability.
Optimization of binding affinities in chemical space with generative pretrained transformer and deep reinforcement learning
The SGPT-RL method achieved better results than Reinvent on the ACE2 task, where molecular docking was used as the optimization goal.
COLA: Cross-city Mobility Transformer for Human Trajectory Simulation
To address these challenges, we have tailored a Cross-city mObiLity trAnsformer (COLA) with a dedicated model-agnostic transfer framework by effectively transferring cross-city knowledge for human trajectory simulation.
A Topological Perspective on Demystifying GNN-Based Link Prediction Performance
Despite the widespread belief that low-degree nodes exhibit poorer LP performance, our empirical findings provide nuances to this viewpoint and prompt us to propose a better metric, Topological Concentration (TC), based on the intersection of the local subgraph of each node with the ones of its neighbors.
Spatial Knowledge-Infused Hierarchical Learning: An Application in Flood Mapping on Earth Imagery
The problem is challenging due to the sparse and noisy input labels, spatial uncertainty within the label inference process, and high computational costs associated with a large number of sample locations.
Every Node is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering
In this paper, we propose to dynamically learn the weights of SSL tasks for different nodes and fuse the embeddings learned from different SSL tasks to boost performance.
Disentangled Condensation for Large-scale Graphs
Graph condensation has emerged as an intriguing technique to provide Graph Neural Networks for large-scale graphs with a more compact yet informative small graph to save the expensive costs of large-scale graph learning.
Multi-Granularity Regularized Re-Balancing for Class Incremental Learning
Re-balancing methods are used to alleviate the influence of data imbalance; however, we empirically discover that they would under-fit new classes.
Few-Shot Specific Emitter Identification via Hybrid Data Augmentation and Deep Metric Learning
Specific emitter identification (SEI) is a potential physical layer authentication technology, which is one of the most critical complements of upper layer authentication.
Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS "Cold-Start"
In the first step, we train different sub-predictors on different types of available low-fidelity information to extract beneficial knowledge as low-fidelity experts.
Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation
Goal-conditioned hierarchical reinforcement learning (HRL) provides a promising direction to tackle this challenge by introducing a hierarchical structure to decompose the search space, where the low-level policy predicts primitive actions in the guidance of the goals derived from the high-level policy.
Hierarchical Reinforcement Learning
Multi-agent Reinforcement Learning
+2
MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perception
We believe that these hallucinations are partially due to the models' struggle with understanding what they can and cannot perceive from images, a capability we refer to as self-awareness in perception.
Generalizable control for quantum parameter estimation through reinforcement learning
Measurement and estimation of parameters are essential for science and engineering, where one of the main quests is to find systematic schemes that can achieve high precision.
Quantum Physics Mesoscale and Nanoscale Physics
Variational Inference with NoFAS: Normalizing Flow with Adaptive Surrogate for Computationally Expensive Models
To reduce the computational cost without sacrificing inferential accuracy, we propose Normalizing Flow with Adaptive Surrogate (NoFAS), an optimization strategy that alternatively updates the normalizing flow parameters and surrogate model parameters.
Multiway Ensemble Kalman Filter
In this work, we study the emergence of sparsity and multiway structures in second-order statistical characterizations of dynamical processes governed by partial differential equations (PDEs).
LAR-SR: A Local Autoregressive Model for Image Super-Resolution
Previous super-resolution (SR) approaches often formulate SR as a regression problem and pixel wise restoration, which leads to a blurry and unreal SR output.
Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation
This fine-tuning allows the model to generate explanations that convey the compatibility relationships between items.
Hidden Talents of the Variational Autoencoder
Variational autoencoders (VAE) represent a popular, flexible form of deep generative model that can be stochastically fit to samples from a given random process using an information-theoretic variational bound on the true underlying distribution.
Predicting Solar Flares Using CNN and LSTM on Two Solar Cycles of Active Region Data
We consider the flare prediction problem that distinguishes flare-imminent active regions that produce an M- or X-class flare in the future 24 hours, from quiet active regions that do not produce any flare within $\pm 24$ hours.
Spatial-temporal Concept based Explanation of 3D ConvNets
Recent studies have achieved outstanding success in explaining 2D image recognition ConvNets.
DartBlur: Privacy Preservation With Detection Artifact Suppression
Facial information is particularly sensitive in this regard.
Spatial Pathomics Toolkit for Quantitative Analysis of Podocyte Nuclei with Histology and Spatial Transcriptomics Data in Renal Pathology
Podocytes, specialized epithelial cells that envelop the glomerular capillaries, play a pivotal role in maintaining renal health.
Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
In this work, we focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories.
Variational Resampling Based Assessment of Deep Neural Networks under Distribution Shift
A novel variational inference based resampling framework is proposed to evaluate the robustness and generalization capability of deep learning models with respect to distribution shift.
The Sylvester Graphical Lasso (SyGlasso)
We apply the SyGlasso to an electroencephalography (EEG) study to compare the brain connectivity of alcoholic and nonalcoholic subjects.
Energy-Aware DNN Graph Optimization
Unlike existing work in deep neural network (DNN) graphs optimization for inference performance, we explore DNN graph optimization for energy awareness and savings for power- and resource-constrained machine learning devices.
Learning Dynamic Preference Structure Embedding From Temporal Networks
Our proposed Dynamic Preference Structure (DPS) framework consists of two stages: structure sampling and graph fusion.
Contrastively-reinforced Attention Convolutional Neural Network for Fine-grained Image Recognition
The evaluation information is backpropagated and forces the classification stream to improve its awareness of visual attention, which helps classification.
Ranked #25 on
Fine-Grained Image Classification
on Stanford Cars
Coping with Change: Learning Invariant and Minimum Sufficient Representations for Fine-Grained Visual Categorization
Fine-grained visual categorization (FGVC) is a challenging task due to similar visual appearances between various species.
OpenMix+: Revisiting Data Augmentation for Open Set Recognition
In this paper, we point out that balancing between structural risk and open space risk is crucial for open set recognition, and re-formalize it as open set structural risk.
Nonparametric Topic Modeling with Neural Inference
Moreover, we also propose HiTM-VAE, where the document-specific topic distributions are generated in a hierarchical manner.
A Deeply-Recursive Convolutional Network for Crowd Counting
The estimation of crowd count in images has a wide range of applications such as video surveillance, traffic monitoring, public safety and urban planning.
Hu-Fu: Hardware and Software Collaborative Attack Framework against Neural Networks
So, in this paper, we propose a hardware-software collaborative attack framework to inject hidden neural network Trojans, which works as a back-door without requiring manipulating input images and is flexible for different scenarios.
A Counter-Forensic Method for CNN-Based Camera Model Identification
We examine in this paper the problem of identifying the camera model or type that was used to take an image and that can be spoofed.
PoTrojan: powerful neural-level trojan designs in deep learning models
With the popularity of deep learning (DL), artificial intelligence (AI) has been applied in many areas of human life.
Phonetic and Graphemic Systems for Multi-Genre Broadcast Transcription
As the combination approaches become more complicated the difference between the phonetic and graphemic systems further decreases.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Telepath: Understanding Users from a Human Vision Perspective in Large-Scale Recommender Systems
This paper proposes Telepath, a vision-based bionic recommender system model, which understands users from such perspective.
LADDER: A Human-Level Bidding Agent for Large-Scale Real-Time Online Auctions
We present LADDER, the first deep reinforcement learning agent that can successfully learn control policies for large-scale real-world problems directly from raw inputs composed of high-level semantic information.
Future Word Contexts in Neural Network Language Models
Instead of using a recurrent unit to capture the complete future word contexts, a feedforward unit is used to model a finite number of succeeding, future, words.
A Deep Learning Approach for Blind Drift Calibration of Sensor Networks
Temporal drift of sensory data is a severe problem impacting the data quality of wireless sensor networks (WSNs).
Exploring the Regularity of Sparse Structure in Convolutional Neural Networks
Since memory reference is more than two orders of magnitude more expensive than arithmetic operations, the regularity of sparse structure leads to more efficient hardware design.
Fast Change Point Detection on Dynamic Social Networks
In this work we devise an effective and efficient three-step-approach for detecting change points in dynamic networks under the snapshot model.
ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA
Evaluated on the LSTM for speech recognition benchmark, ESE is 43x and 3x faster than Core i7 5930k CPU and Pascal Titan X GPU implementations.
Do They All Look the Same? Deciphering Chinese, Japanese and Koreans by Fine-Grained Deep Learning
We find that Chinese, Japanese and Koreans do exhibit substantial differences in certain attributes, such as bangs, smiling, and bushy eyebrows.
Improving the Speed of Response of Learning Algorithms Using Multiple Models
During the past two decades, the first author has worked on numerous methods for improving the stability, robustness, and performance of adaptive systems using multiple models and the other authors have collaborated with him on some of them.
Sparse K-Means with $\ell_{\infty}/\ell_0$ Penalty for High-Dimensional Data Clustering
Nevertheless, this framework has two serious drawbacks: One is that the solution of the framework unavoidably involves a considerable portion of redundant noise features in many situations, and the other is that the framework neither offers intuitive explanations on why this framework can select relevant features nor leads to any theoretical guarantee for feature selection consistency.
A Survey of FPGA Based Neural Network Accelerator
Various FPGA based accelerator designs have been proposed with software and hardware optimization techniques to achieve high speed and energy efficiency.
Hardware Architecture
User Information Augmented Semantic Frame Parsing using Coarse-to-Fine Neural Networks
The results show that our approach leverages such simple user information to outperform state-of-the-art approaches by 0. 25% for intent detection and 0. 31% for slot filling using standard training data.
Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks
These errors are not accounted for by the standard confidence estimation schemes and are hard to rectify in the upstream and downstream processing.
A New Concept of Deep Reinforcement Learning based Augmented General Tagging System
In this paper, a new deep reinforcement learning based augmented general tagging system is proposed.
NEURAL MALWARE CONTROL WITH DEEP REINFORCEMENT LEARNING
Antimalware products are a key component in detecting malware attacks, and their engines typically execute unknown programs in a sandbox prior to running them on the native operating system.
CNNSAT: Fast, Accurate Boolean Satisfiability using Convolutional Neural Networks
Boolean satisfiability (SAT) is one of the most well-known NP-complete problems and has been extensively studied.
A Bayesian Nonparametric Topic Model with Variational Auto-Encoders
On the other hand, different with the other BNP topic models, the inference of iTM-VAE is modeled by neural networks, which has rich representation capacity and can be computed in a simple feed-forward manner.
A New Concept of Deep Reinforcement Learning based Augmented General Sequence Tagging System
In this paper, a new deep reinforcement learning based augmented general sequence tagging system is proposed.
Unique Sharp Local Minimum in $\ell_1$-minimization Complete Dictionary Learning
First, we obtain a necessary and sufficient norm condition for the reference dictionary $D^*$ to be a sharp local minimum of the expected $\ell_1$ objective function.
Transferrable Prototypical Networks for Unsupervised Domain Adaptation
Specifically, we present Transferrable Prototypical Networks (TPN) for adaptation such that the prototypes for each class in source and target domains are close in the embedding space and the score distributions predicted by prototypes separately on source and target data are similar.
New Era of Deeplearning-Based Malware Intrusion Detection: The Malware Detection and Prediction Based On Deep Learning
With the development of artificial intelligence algorithms like deep learning models and the successful applications in many different fields, further similar trails of deep learning technology have been made in cyber security area.
Single Training Dimension Selection for Word Embedding with PCA
In this paper, we present a fast and reliable method based on PCA to select the number of dimensions for word embeddings.
Non-native Speaker Verification for Spoken Language Assessment
These systems are explored for non-native spoken English data in this paper.
Review of Learning-based Longitudinal Motion Planning for Autonomous Vehicles: Research Gaps between Self-driving and Traffic Congestion
Some suggestions towards congestion mitigation for future mMP studies are proposed: i) enrich data collection to facilitate the congestion learning, ii) incorporate non-imitation learning methods to combine traffic efficiency into a safety-oriented technical route, and iii) integrate domain knowledge from the traditional car following (CF) theory to improve the string stability of mMP.
Application of Pre-training Models in Named Entity Recognition
Then, we apply these pre-training models to a NER task by fine-tuning, and compare the effects of the different model architecture and pre-training tasks on the NER task.
Video-based Person Re-Identification using Gated Convolutional Recurrent Neural Networks
In this paper, we introduce a novel gating mechanism to deep neural networks.
Optical Flow Estimation
Video-Based Person Re-Identification
FTT-NAS: Discovering Fault-Tolerant Convolutional Neural Architecture
By inspecting the discovered architectures, we find that the operation primitives, the weight quantization range, the capacity of the model, and the connection pattern have influences on the fault resilience capability of NN models.
Enabling Efficient and Flexible FPGA Virtualization for Deep Learning in the Cloud
Currently, the majority of FPGA-based DNN accelerators in the cloud run in a time-division multiplexing way for multiple users sharing a single FPGA, and require re-compilation with $\sim$100 s overhead.
Differentially Private Algorithms for Statistical Verification of Cyber-Physical Systems
We also show that the standard exponential mechanism that randomizes the output of an algorithm to achieve differential privacy fails to do so in the context of sequential algorithms.
Statistically Model Checking PCTL Specifications on Markov Decision Processes via Reinforcement Learning
Probabilistic Computation Tree Logic (PCTL) is frequently used to formally specify control objectives such as probabilistic reachability and safety.
The Ivory Tower Lost: How College Students Respond Differently than the General Public to the COVID-19 Pandemic
Recently, the pandemic of the novel Coronavirus Disease-2019 (COVID-19) has presented governments with ultimate challenges.
In the Eyes of the Beholder: Analyzing Social Media Use of Neutral and Controversial Terms for COVID-19
To model the substantive difference of tweets with controversial terms and those with non-controversial terms, we apply topic modeling and LIWC-based sentiment analysis.
Communication Lower Bound in Convolution Accelerators
Evaluations based on the 65nm technology demonstrate that the proposed architecture nearly reaches the theoretical minimum communication in a three-level memory hierarchy and it is computation dominant.
Distributed, Parallel, and Cluster Computing Hardware Architecture
A Comprehensive Survey of Grammar Error Correction
More importantly, we discuss four kinds of basic approaches, including statistical machine translation based approach, neural machine translation based approach, classification based approach and language model based approach, six commonly applied performance boosting techniques for GEC systems and two data augmentation methods.
Learning Semantic Program Embeddings with Graph Interval Neural Network
We have also created a neural bug detector based on GINN to catch null pointer deference bugs in Java code.
A Complex KBQA System using Multiple Reasoning Paths
Multi-hop knowledge based question answering (KBQA) is a complex task for natural language understanding.
Precisely Predicting Acute Kidney Injury with Convolutional Neural Network Based on Electronic Health Record Data
Compared with the existing AKI predictors, the predictor in this work greatly improves the precision of early prediction of AKI by using the Convolutional Neural Network architecture and a more concise input vector.
Exploring the Potential of Low-bit Training of Convolutional Neural Networks
For training a variety of models on CIFAR-10, using 1-bit mantissa and 2-bit exponent is adequate to keep the accuracy loss within $1\%$.
Learning Monotone Dynamics by Neural Networks
For monotonicity constraints, we propose to use nonnegative neural networks and batch normalization.
2nd Place Solution for Waymo Open Dataset Challenge -- 2D Object Detection
A practical autonomous driving system urges the need to reliably and accurately detect vehicles and persons.
1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking
This technical report presents the online and real-time 2D and 3D multi-object tracking (MOT) algorithms that reached the 1st places on both Waymo Open Dataset 2D tracking and 3D tracking challenges.
1st Place Solution for Waymo Open Dataset Challenge -- 3D Detection and Domain Adaptation
We proposed a one-stage, anchor-free and NMS-free 3D point cloud object detector AFDet, using object key-points to encode the 3D attributes, and to learn an end-to-end point cloud object detection without the need of hand-engineering or learning the anchors.
Monitoring Depression Trend on Twitter during the COVID-19 Pandemic
The COVID-19 pandemic has severely affected people's daily lives and caused tremendous economic loss worldwide.
Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification
Some works in the optimization of deep neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better.
Physical Adversarial Attack on Vehicle Detector in the Carla Simulator
In this paper, we tackle the issue of physical adversarial examples for object detectors in the wild.
Shift Equivariance in Object Detection
Robustness to small image translations is a highly desirable property for object detectors.
SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Context
In this article, we describe our data collection procedure and propose evaluation metrics for multilabel classification of urban sound tags.
A Survey of FPGA-Based Robotic Computing
On the other hand, FPGA-based robotic accelerators are becoming increasingly competitive alternatives, especially in latency-critical and power-limited scenarios.
Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms
We benchmark commonly used multi-agent deep reinforcement learning (MARL) algorithms on a variety of cooperative multi-agent games.
Explore the Potential of CNN Low Bit Training
Through this dynamic precision framework, we can reduce the bit-width of convolution, which is the most computational cost, while keeping the training process close to the full precision floating-point training.
How Effective is Task-Agnostic Data Augmentation for Pretrained Transformers?
Task-agnostic forms of data augmentation have proven widely effective in computer vision, even on pretrained models.
