Search Results for author:
Found 163 papers, 49 papers with code
Incorporating Casual Analysis into Diversified and Logical Response Generation
Although the Conditional Variational Auto-Encoder (CVAE) model can generate more diversified responses than the traditional Seq2Seq model, the responses often have low relevance with the input words or are illogical with the question.
Meta contrastive label correction for financial time series
One is that our proposed method can automatically generate correct labels for noisy time series patterns, while at the same time, the method is capable of boosting classification performance on this new labeled dataset.
Heterogeneous Graph Contrastive Learning for Recommendation
In light of this, we propose a Heterogeneous Graph Contrastive Learning (HGCL), which is able to incorporate heterogeneous relational semantics into the user-item interaction modeling with contrastive learning-enhanced knowledge transfer across different views.
Multi-Modal Self-Supervised Learning for Recommendation
The online emergence of multi-modal sharing platforms (eg, TikTok, Youtube) is powering personalized recommender systems to incorporate various modalities (eg, visual, textual and acoustic) into the latent user representations.
Sizing Grid-Connected Wind Power Generation and Energy Storage with Wake Effect and Endogenous Uncertainty: A Distributionally Robust Method
In this paper, a bi-objective distributionally robust optimization (DRO) model is proposed to determine the capacities of wind power generation and ESSs considering the wake effect.
STAGE: Span Tagging and Greedy Inference Scheme for Aspect Sentiment Triplet Extraction
Hence, we propose a novel approach, Span TAgging and Greedy infErence (STAGE), to extract sentiment triplets in span-level, where each span may consist of multiple words and play different roles simultaneously.
A Benchmark for Structured Extractions from Complex Documents
Understanding visually-rich business documents to extract structured data and automate business workflows has been receiving attention both in academia and industry.
Knowledge Graph Enhanced Relation Extraction Datasets
Knowledge-enhanced methods that take advantage of auxiliary knowledge graphs recently emerged in relation extraction, and they surpass traditional text-based relation extraction methods.
Sequential Topic Selection Model with Latent Variable for Topic-Grounded Dialogue
To address the problem, in this paper we propose a novel approach, named Sequential Global Topic Attention (SGTA) to exploit topic transition over all conversations in a subtle way for better modeling post-to-response topic-transition and guiding the response generation to the current conversation.
HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold
Conventional event detection models under supervised learning settings suffer from the inability of transfer to newly-emerged event types owing to lack of sufficient annotations.
Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network
The proposed model mainly focuses on the evidence selection phase of long document question answering.
Metric Distribution to Vector: Constructing Data Representation via Broad-Scale Discrepancies
Graph embedding provides a feasible methodology to conduct pattern classification for graph-structured data by mapping each data into the vectorial space.
Unsupervised Hashing with Semantic Concept Mining
Recently, to improve the unsupervised image retrieval performance, plenty of unsupervised hashing methods have been proposed by designing a semantic similarity matrix, which is based on the similarities between image features extracted by a pre-trained CNN model.
Incorporating Causal Analysis into Diversified and Logical Response Generation
Although the Conditional Variational AutoEncoder (CVAE) model can generate more diversified responses than the traditional Seq2Seq model, the responses often have low relevance with the input words or are illogical with the question.
Multi-level Contrastive Learning Framework for Sequential Recommendation
Different from the previous contrastive learning-based methods for SR, MCLSR learns the representations of users and items through a cross-view contrastive learning paradigm from four specific views at two different levels (i. e., interest- and feature-level).
Improving Personality Consistency in Conversation by Persona Extending
Endowing chatbots with a consistent personality plays a vital role for agents to deliver human-like interactions.
Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning
Specifically, we first construct local and non-local graphs for user/item in KG, exploring more KG facts for KGR.
Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting
These results suggest that we can design efficient and effective models as long as they solve the indistinguishability of samples, without being limited to STGNNs.
Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection
Instead of directly exploiting the pseudo labels produced by the teacher detector, we take the first attempt at reducing their deviation from ground truth using dual polishing learning, where two differently structured polishing networks are elaborately developed and trained using synthesized paired pseudo labels and the corresponding ground truth for categories and bounding boxes on the given annotated objects, respectively.
E2FIF: Push the limit of Binarized Deep Imagery Super-resolution using End-to-end Full-precision Information Flow
Binary neural network (BNN) provides a promising solution to deploy parameter-intensive deep single image super-resolution (SISR) models onto real devices with limited storage and computational resources.
Temporal Link Prediction via Adjusted Sigmoid Function and 2-Simplex Sructure
Temporal network link prediction is an important task in the field of network science, and has a wide range of applications in practical scenarios.
Person-job fit estimation from candidate profile and related recruitment history with co-attention neural networks
Existing studies on person-job fit, however, mainly focus on calculating the similarity between the candidate resumes and the job postings on the basis of their contents, without taking the recruiters' experience (i. e., historical successful recruitment records) into consideration.
Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting
However, intuitively, traffic data encompasses two different kinds of hidden time series signals, namely the diffusion signals and inherent signals.
Ranked #3 on
Traffic Prediction
on METR-LA
Parameter Convex Neural Networks
Deep learning utilizing deep neural networks (DNNs) has achieved a lot of success recently in many important areas such as computer vision, natural language processing, and recommendation systems.
Relational Triple Extraction: One Step is Enough
Extracting relational triples from unstructured text is an essential task in natural language processing and knowledge graph construction.
Automatic Noisy Label Correction for Fine-Grained Entity Typing
Fine-grained entity typing (FET) aims to assign proper semantic types to entity mentions according to their context, which is a fundamental task in various entity-leveraging applications.
Declaration-based Prompt Tuning for Visual Question Answering
In recent years, the pre-training-then-fine-tuning paradigm has yielded immense success on a wide spectrum of cross-modal tasks, such as visual question answering (VQA), in which a visual-language (VL) model is first optimized via self-supervised task objectives, e. g., masked language modeling (MLM) and image-text matching (ITM), and then fine-tuned to adapt to downstream task (e. g., VQA) via a brand-new objective function, e. g., answer prediction.
Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization
Content mismatch usually occurs when data from one modality is translated to another, e. g. language learners producing mispronunciations (errors in speech) when reading a sentence (target text) aloud.
Multi-core fiber enabled fading noise suppression in φ-OFDR based quantitative distributed vibration sensing
Coherent fading has been regarded as a critical issue in phase-sensitive optical frequency domain reflectometry ({\phi}-OFDR) based distributed fiber-optic sensing.
Enhance Ambiguous Community Structure via Multi-strategy Community Related Link Prediction Method with Evolutionary Process
To address this issue, in this paper, we design a new community attribute based link prediction strategy HAP and propose a two-step community enhancement algorithm with automatic evolution process based on HAP.
Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
Different from traditional contrastive learning methods which generate two graph views by uniform data augmentation schemes such as corruption or dropping, we comprehensively consider three different graph views for KG-aware recommendation, including global-level structural view, local-level collaborative and semantic views.
Cross-Lingual Phrase Retrieval
In this paper, we propose XPR, a cross-lingual phrase retriever that extracts phrase representations from unlabeled example sentences.
BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that aims to align aspects and corresponding sentiments for aspect-specific sentiment polarity inference.
An Optimal Control Method to Compute the Most Likely Transition Path for Stochastic Dynamical Systems with Jumps
One of the challenges to calculate the most likely transition path for stochastic dynamical systems under non-Gaussian L\'evy noise is that the associated rate function can not be explicitly expressed by paths.
Multi-view Intent Disentangle Graph Networks for Bundle Recommendation
Specifically, MIDGN disentangles the user's intents from two different perspectives, respectively: 1) In the global level, MIDGN disentangles the user's intent coupled with inter-bundle items; 2) In the Local level, MIDGN disentangles the user's intent coupled with items within each bundle.
Optimal configuration of cooperative stationary and mobile energy storage considering ambient temperature: A case for Winter Olympic Game
The international mega-event, such as the Winter Olympic Game, has been considered as one of the most carbon intensive activities worldwide.
Contrastive Meta Learning with Behavior Multiplicity for Recommendation
In addition, to capture the diverse multi-behavior patterns, we design a contrastive meta network to encode the customized behavior heterogeneity for different users.
Underwater Differential Game: Finite-Time Target Hunting Task with Communication Delay
Simulations show that underwater disturbances have a large impact on the system considering communication delay.
Gradient-guided Unsupervised Text Style Transfer via Contrastive Learning
(2) Style misclassification.
Credit Valuation Adjustment with Replacement Closeout: Theory and Algorithms
In contrast to the risk-free closeout, the replacement closeout renders a nonlinear valuation system, which constitutes the major difficulty in the valuation of the counterparty credit risk.
Meta-CPR: Generalize to Unseen Large Number of Agents with Communication Pattern Recognition Module
The number of agents can grow or an environment sometimes needs to interact with a changing number of agents in real-world scenarios.
RATE: Overcoming Noise and Sparsity of Textual Features in Real-Time Location Estimation
Real-time location inference of social media users is the fundamental of some spatial applications such as localized search and event detection.
Bridge the Gap Between CV and NLP! An Optimization-based Textual Adversarial Attack Framework
In this paper, we instantiate our framework with an attack algorithm named Textual Projected Gradient Descent (T-PGD).
Geometry-Entangled Visual Semantic Transformer for Image Captioning
However, those fusion-based models, they are still criticized for the lack of geometry information for inter and intra attention refinement.
Approaching the Transient Stability Boundary of a Power System: Theory and Applications
Estimating the stability boundary is a fundamental and challenging problem in transient stability studies.
Context-aware Entity Typing in Knowledge Graphs
Knowledge graph entity typing aims to infer entities' missing types in knowledge graphs which is an important but under-explored issue.
Storage and Transmission Capacity Requirements of a Remote Solar Power Generation System
Large solar power stations usually locate in remote areas and connect to the main grid via a long transmission line.
Multi-granularity Textual Adversarial Attack with Behavior Cloning
Furthermore, we propose a reinforcement-learning based method to train a multi-granularity attack agent through behavior cloning with the expert knowledge from our MAYA algorithm to further reduce the query times.
Heterogeneous Graph Neural Network with Multi-view Representation Learning
Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph.
A Graph Data Augmentation Strategy with Entropy Preservation
Considering the preservation of graph entropy, we propose an effective strategy to generate randomly perturbed training data but maintain both graph topology and graph entropy.
Locality Relationship Constrained Multi-view Clustering Framework
LRC-MCF aims to explore the diversity, geometric, consensus and complementary information among different views, by capturing the locality relationship information and the common similarity relationships among multiple views.
NTIRE 2021 Multi-modal Aerial View Object Classification Challenge
In this paper, we introduce the first Challenge on Multi-modal Aerial View Object Classification (MAVOC) in conjunction with the NTIRE 2021 workshop at CVPR.
Global Context Enhanced Graph Neural Networks for Session-based Recommendation
In GCE-GNN, we propose a novel global-level item representation learning layer, which employs a session-aware attention mechanism to recursively incorporate the neighbors' embeddings of each node on the global graph.
Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction
The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions.
Exploiting Global Contextual Information for Document-level Named Entity Recognition
To this end, we propose a model called Global Context enhanced Document-level NER (GCDoc) to leverage global contextual information from two levels, i. e., both word and sentence.
DARNet: Dual-Attention Residual Network for Automatic Diagnosis of COVID-19 via CT Images
The ongoing global pandemic of Coronavirus Disease 2019 (COVID-19) poses a serious threat to public health and the economy.
On the Time-Inconsistent Deterministic Linear-Quadratic Control
By studying the solvability of the Riccati equation, we show the existence and uniqueness of the linear equilibrium for the time-inconsistent LQ problem.
A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting
The most recent researches on domain adaption focus on giving the model a better initialization, rather than optimizing the adaptation process.
Research of Damped Newton Stochastic Gradient Descent Method for Neural Network Training
First-order methods like stochastic gradient descent(SGD) are recently the popular optimization method to train deep neural networks (DNNs), but second-order methods are scarcely used because of the overpriced computing cost in getting the high-order information.
Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas
By the proposed physical regularization, our method can generate HDRs which are not only visually appealing but also physically plausible.
Context-aware Biaffine Localizing Network for Temporal Sentence Grounding
This paper addresses the problem of temporal sentence grounding (TSG), which aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query.
Understanding Heart-Failure Patients EHR Clinical Features via SHAP Interpretation of Tree-Based Machine Learning Model Predictions
We examined whether machine learning models, more specifically the XGBoost model, can accurately predict patient stage based on EHR, and we further applied the SHapley Additive exPlanations (SHAP) framework to identify informative features and their interpretations.
A Data-Centric Framework for Composable NLP Workflows
Empirical natural language processing (NLP) systems in application domains (e. g., healthcare, finance, education) involve interoperation among multiple components, ranging from data ingestion, human annotation, to text retrieval, analysis, generation, and visualization.
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach
An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interaction, which is usually not affordable for large-scale experiments.
Graph Classification Based on Skeleton and Component Features
Most existing popular methods for learning graph embedding only consider fixed-order global structural features and lack structures hierarchical representation.
Large Deviations for SDE driven by Heavy-tailed Lévy Processes
We obtain sample-path large deviations for a class of one-dimensional stochastic differential equations with bounded drifts and heavy-tailed L\'evy processes.
Probability 60H10, 60F10, 60J76
Representation Learning of Reconstructed Graphs Using Random Walk Graph Convolutional Network
Graphs are often used to organize data because of their simple topological structure, and therefore play a key role in machine learning.
A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition
Recently, it has attracted much attention to build reliable named entity recognition (NER) systems using limited annotated data.
Ranked #3 on
Named Entity Recognition (NER)
on SciERC
(using extra training data)
Low Resource Named Entity Recognition
named-entity-recognition
+2
FLAR: A Unified Prototype Framework for Few-Sample Lifelong Active Recognition
To address this demand, in this paper, we propose a unified framework towards Few-sample Lifelong Active Recognition (FLAR), which aims at performing active recognition on progressively arising novel categories that only have few training samples.
Generative Fairness Teaching
We propose a generative fairness teaching framework that provides a model with not only real samples but also synthesized samples to compensate the data biases during training.
Context-Aware Temperature for Language Modeling
Current practices to apply temperature scaling assume either a fixed, or a manually-crafted dynamically changing schedule.
Contextual Temperature for Language Modeling
Temperature scaling has been widely used as an effective approach to control the smoothness of a distribution, which helps the model performance in various tasks.
Self-attention Comparison Module for Boosting Performance on Retrieval-based Open-Domain Dialog Systems
Since the pre-trained language models are widely used, retrieval-based open-domain dialog systems, have attracted considerable attention from researchers recently.
Ultra-Fast, Low-Storage, Highly Effective Coarse-grained Selection in Retrieval-based Chatbot by Using Deep Semantic Hashing
Specifically, in our proposed DSHC model, a hashing optimizing module that consists of two autoencoder models is stacked on a trained dense representation model, and three loss functions are designed to optimize it.
Accelerated, Scalable and Reproducible AI-driven Gravitational Wave Detection
The development of reusable artificial intelligence (AI) models for wider use and rigorous validation by the community promises to unlock new opportunities in multi-messenger astrophysics.
Data-Driven Dispatchable Regions with Potentially Active Boundaries for Renewable Power Generation: Concept and Construction
State-of-the-art dispatchable region (DR) research has studied how system operational constraints influence the DR but has seldom considered the effect of the uncertainty features of RPG outputs.
Exploiting Group-level Behavior Pattern forSession-based Recommendation
In RNMSR, we propose to learn the user preference from both instance-level and group-level, respectively: (i) instance-level, which employs GNNs on a similarity-based item-pairwise session graph to capture the users' preference in instance-level.
Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation
To capture temporal information from previous frames, we use a memory network to refine the mask of current frame by retrieving historic masks in a temporal graph.
One-shot visual object segmentation
Semantic Segmentation
+1
Com-DDPG: A Multiagent Reinforcement Learning-based Offloading Strategy for Mobile Edge Computing
First, we discuss the task dependency model, task priority model, energy consumption model, and average latency from the perspective of server clusters and multidependence on mobile tasks.
Decision Making
Edge-computing
+1
Distributed, Parallel, and Cluster Computing
Multiagent Systems
Unsupervised Alternating Optimization for Blind Hyperspectral Imagery Super-resolution
One of the main reason comes from the fact that the predefined degeneration models (e. g. blur in spatial domain) utilized by most HSI SR methods often exist great discrepancy with the real one, which results in these deep models overfit and ultimately degrade their performance on real data.
Meta-Generating Deep Attentive Metric for Few-shot Classification
To mitigate this problem, we present a novel deep metric meta-generation method that turns to an orthogonal direction, ie, learning to adaptively generate a specific metric for a new FSL task based on the task description (eg, a few labelled samples).
Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization
To preserve the knowledge we learn from previous instances, we proposed a method to protect the path by restricting the gradient updates of one instance from overriding past updates calculated from previous instances if these instances are not similar.
Differentiable Top-k with Optimal Transport
Finding the k largest or smallest elements from a collection of scores, i. e., top-k operation, is an important model component widely used in information retrieval, machine learning, and data mining.
Exploring Global Information for Session-based Recommendation
Based on BGNN, we propose a novel approach, called Session-based Recommendation with Global Information (SRGI), which infers the user preferences via fully exploring global item-transitions over all sessions from two different perspectives: (i) Fusion-based Model (SRGI-FM), which recursively incorporates the neighbor embeddings of each node on global graph into the learning process of session level item representation; and (ii) Constrained-based Model (SRGI-CM), which treats the global-level item-transition information as a constraint to ensure the learned item embeddings are consistent with the global item-transition.
AirConcierge: Generating Task-Oriented Dialogue via Efficient Large-Scale Knowledge Retrieval
Despite recent success in neural task-oriented dialogue systems, developing such a real-world system involves accessing large-scale knowledge bases (KBs), which cannot be simply encoded by neural approaches, such as memory network mechanisms.
User-based Network Embedding for Collective Opinion Spammer Detection
Due to the huge commercial interests behind online reviews, a tremendousamount of spammers manufacture spam reviews for product reputation manipulation.
Target Guided Emotion Aware Chat Machine
The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions.
A Survey on Recent Advances in Sequence Labeling from Deep Learning Models
Sequence labeling (SL) is a fundamental research problem encompassing a variety of tasks, e. g., part-of-speech (POS) tagging, named entity recognition (NER), text chunking, etc.
Deep Cross-modal Hashing via Margin-dynamic-softmax Loss
Finally, by minimizing the novel \textit{margin-dynamic-softmax loss}, the modality-specific hashing networks can be trained to generate hash codes which can simultaneously preserve the cross-modal similarity and abundant semantic information well.
Question Answering with Long Multiple-Span Answers
To this end, we present MASH-QA, a Multiple Answer Spans Healthcare Question Answering dataset from the consumer health domain, where answers may need to be excerpted from multiple, non-consecutive parts of text spanned across a long document.
Deep Kernel Supervised Hashing for Node Classification in Structural Networks
However, nearly all the existing network embedding based methods are hard to capture the actual category features of a node because of the linearly inseparable problem in low-dimensional space; meanwhile they cannot incorporate simultaneously network structure information and node label information into network embedding.
Differentiable Top-$k$ with Optimal Transport
The top-$k$ operation, i. e., finding the $k$ largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining.
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
Which Kind Is Better in Open-domain Multi-turn Dialog,Hierarchical or Non-hierarchical Models? An Empirical Study
Thus, in this paper, we will measure systematically nearly all representative hierarchical and non-hierarchical models over the same experimental settings to check which kind is better.
Representation Learning of Graphs Using Graph Convolutional Multilayer Networks Based on Motifs
The graph structure is a commonly used data storage mode, and it turns out that the low-dimensional embedded representation of nodes in the graph is extremely useful in various typical tasks, such as node classification, link prediction , etc.
Remix: Rebalanced Mixup
In this work, we propose a new regularization technique, Remix, that relaxes Mixup's formulation and enables the mixing factors of features and labels to be disentangled.
Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization
In this paper, we propose a noise-agnostic method to achieve robust neural network performance against any noise setting.
A Hybrid Natural Language Generation System Integrating Rules and Deep Learning Algorithms
This paper proposes an enhanced natural language generation system combining the merits of both rule-based approaches and modern deep learning algorithms, boosting its performance to the extent where the generated textual content is capable of exhibiting agile human-writing styles and the content logic of which is highly controllable.
Ball k-means
The assigned cluster of the points in the stable area is not changed in the current iteration while the points in the annulus area will be adjusted within a few neighbor clusters in the current iteration.
Knowledge Injection into Dialogue Generation via Language Models
First, we train a large-scale language model and query it as textual knowledge.
CmnRec: Sequential Recommendations with Chunk-accelerated Memory Network
Specifically, our framework divides proximal information units into chunks, and performs memory access at certain time steps, whereby the number of memory operations can be greatly reduced.
PONE: A Novel Automatic Evaluation Metric for Open-Domain Generative Dialogue Systems
Through extensive experiments, the learning-based metrics are demonstrated that they are the most effective evaluation metrics for open-domain generative dialogue systems.
Crowd Counting via Hierarchical Scale Recalibration Network
Extensive experiments on crowd counting datasets (ShanghaiTech, MALL, WorldEXPO'10, and UCSD) show that our HSRNet can deliver superior results over all state-of-the-art approaches.
Dynamic Graph Correlation Learning for Disease Diagnosis with Incomplete Labels
In this work, we propose a Disease Diagnosis Graph Convolutional Network (DD-GCN) that presents a novel view of investigating the inter-dependency among different diseases by using a dynamic learnable adjacency matrix in graph structure to improve the diagnosis accuracy.
Differentiable Top-k Operator with Optimal Transport
The top-k operation, i. e., finding the k largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining.
When to Talk: Chatbot Controls the Timing of Talking during Multi-turn Open-domain Dialogue Generation
Intuitively, a dialogue model that can control the timing of talking autonomously based on the conversation context can chat with humans more naturally.
Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.
Overcoming Catastrophic Forgetting by Generative Regularization
In this paper, we propose a new method to overcome catastrophic forgetting by adding generative regularization to Bayesian inference framework.
Abstract Reasoning with Distracting Features
Abstraction reasoning is a long-standing challenge in artificial intelligence.
Enabling real-time multi-messenger astrophysics discoveries with deep learning
Multi-messenger astrophysics is a fast-growing, interdisciplinary field that combines data, which vary in volume and speed of data processing, from many different instruments that probe the Universe using different cosmic messengers: electromagnetic waves, cosmic rays, gravitational waves and neutrinos.
Learning with Hierarchical Complement Objective
Label hierarchies widely exist in many vision-related problems, ranging from explicit label hierarchies existed in image classification to latent label hierarchies existed in semantic segmentation.
Table-to-Text Natural Language Generation with Unseen Schemas
In this paper, we propose the new task of table-to-text NLG with unseen schemas, which specifically aims to test the generalization of NLG for input tables with attribute types that never appear during training.
AI Matrix: A Deep Learning Benchmark for Alibaba Data Centers
Alibaba has China's largest e-commerce platform.
Natural Adversarial Sentence Generation with Gradient-based Perturbation
This work proposes a novel algorithm to generate natural language adversarial input for text classification models, in order to investigate the robustness of these models.
Stack-VS: Stacked Visual-Semantic Attention for Image Caption Generation
Recently, automatic image caption generation has been an important focus of the work on multimodal translation task.
Position-Aware Self-Attention based Neural Sequence Labeling
Sequence labeling is a fundamental task in natural language processing and has been widely studied.
XSP: Across-Stack Profiling and Analysis of Machine Learning Models on GPUs
Such an endeavor is challenging as the characteristics of an ML model depend on the interplay between the model, framework, system libraries, and the hardware (or the HW/SW stack).
Deep Hashing for Signed Social Network Embedding
Network embedding is a promising way of network representation, facilitating many signed social network processing and analysis tasks such as link prediction and node classification.
Enhanced 3D convolutional networks for crowd counting
Recently, convolutional neural networks (CNNs) are the leading defacto method for crowd counting.
Deep Cross-Modal Hashing with Hashing Functions and Unified Hash Codes Jointly Learning
Specifically, by an iterative optimization algorithm, DCHUC jointly learns unified hash codes for image-text pairs in a database and a pair of hash functions for unseen query image-text pairs.
Discriminative Embedding Autoencoder with a Regressor Feedback for Zero-Shot Learning
Zero-shot learning (ZSL) aims to recognize the novel object categories using the semantic representation of categories, and the key idea is to explore the knowledge of how the novel class is semantically related to the familiar classes.
On the Robustness of Self-Attentive Models
This work examines the robustness of self-attentive neural networks against adversarial input perturbations.
Reinforcement Learning Driven Heuristic Optimization
In this paper, we introduce a novel framework to generate better initial solutions for heuristic algorithms using reinforcement learning (RL), named RLHO.
Evaluating and Enhancing the Robustness of Dialogue Systems: A Case Study on a Negotiation Agent
Moreover, we show that with the adversarial training, we are able to improve the robustness of negotiation agents by 1. 5 points on average against all our attacks.
COCO-GAN: Conditional Coordinate Generative Adversarial Network
The fact that the patch generation process is independent to each other inspires a wide range of new applications: firstly, "Patch-Inspired Image Generation" enables us to generate the entire image based on a single patch.
Vehicle Re-identification in Aerial Imagery: Dataset and Approach
It is capable of explicitly detecting discriminative parts for each specific vehicle and significantly outperforms the evaluated baselines and state-of-the-art vehicle ReID approaches.
COCO-GAN: Generation by Parts via Conditional Coordinating
On the computation side, COCO-GAN has a built-in divide-and-conquer paradigm that reduces memory requisition during training and inference, provides high-parallelism, and can generate parts of images on-demand.
Ranked #1 on
Image Generation
on CelebA-HQ 64x64
Pixel-aware Deep Function-mixture Network for Spectral Super-Resolution
To address this problem, we propose a pixel-aware deep function-mixture network for SSR, which is composed of a new class of modules, termed function-mixture (FM) blocks.
Improving Adversarial Robustness via Guided Complement Entropy
Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model.
Complement Objective Training
Although being a widely-adopted approach, using cross entropy as the primary objective exploits mostly the information from the ground-truth class for maximizing data likelihood, and largely ignores information from the complement (incorrect) classes.
Deep Learning for Multi-Messenger Astrophysics: A Gateway for Discovery in the Big Data Era
We discuss key aspects to realize this endeavor, namely (i) the design and exploitation of scalable and computationally efficient AI algorithms for Multi-Messenger Astrophysics; (ii) cyberinfrastructure requirements to numerically simulate astrophysical sources, and to process and interpret Multi-Messenger Astrophysics data; (iii) management of gravitational wave detections and triggers to enable electromagnetic and astro-particle follow-ups; (iv) a vision to harness future developments of machine and deep learning and cyberinfrastructure resources to cope with the scale of discovery in the Big Data Era; (v) and the need to build a community that brings domain experts together with data scientists on equal footing to maximize and accelerate discovery in the nascent field of Multi-Messenger Astrophysics.
Meta Architecture Search
Neural Architecture Search (NAS) has been quite successful in constructing state-of-the-art models on a variety of tasks.
AI Matrix - Synthetic Benchmarks for DNN
In this work, a synthetic benchmarks framework is firstly proposed to address the above drawbacks of AI benchmarks.
InstaNAS: Instance-aware Neural Architecture Search
Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy.
Policy Certificates: Towards Accountable Reinforcement Learning
The performance of a reinforcement learning algorithm can vary drastically during learning because of exploration.
AirDialogue: An Environment for Goal-Oriented Dialogue Research
However, current datasets are limited in size, and the environment for training agents and evaluating progress is relatively unsophisticated.
Towards Effective Deep Embedding for Zero-Shot Learning
Towards this goal, we present a simple but effective two-branch network to simultaneously map semantic descriptions and visual samples into a joint space, on which visual embeddings are forced to regress to their class-level semantic embeddings and the embeddings crossing classes are required to be distinguishable by a trainable classifier.
Searching Toward Pareto-Optimal Device-Aware Neural Architectures
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding.
Escaping from Collapsing Modes in a Constrained Space
Generative adversarial networks (GANs) often suffer from unpredictable mode-collapsing during training.
Ranked #18 on
Image Generation
on CelebA 64x64
Semi-supervised Transfer Learning for Image Rain Removal
However, previous deep learning methods need to pre-collect a large set of image pairs with/without synthesized rain for training, which tends to make the neural network be biased toward learning the specific patterns of the synthesized rain, while be less able to generalize to real test samples whose rain types differ from those in the training data.
Ranked #7 on
Single Image Deraining
on Test1200
MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning
Recent studies on neural architecture search have shown that automatically designed neural networks perform as good as expert-crafted architectures.
DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures
We propose DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures, optimizing for both device-related (e. g., inference time and memory usage) and device-agnostic (e. g., accuracy and model size) objectives.
Accurate Spectral Super-resolution from Single RGB Image Using Multi-scale CNN
Different from traditional hyperspectral super-resolution approaches that focus on improving the spatial resolution, spectral super-resolution aims at producing a high-resolution hyperspectral image from the RGB observation with super-resolution in spectral domain.
Adaptive Importance Learning for Improving Lightweight Image Super-resolution Network
In this study, we revisit this problem from an orthog- onal view, and propose a novel learning strategy to maxi- mize the pixel-wise fitting capacity of a given lightweight network architecture.
Video Rain Streak Removal by Multiscale Convolutional Sparse Coding
Based on such understanding, we specifically formulate both characteristics into a multiscale convolutional sparse coding (MS-CSC) model for the video rain streak removal task.
Participation of an energy hub in electricity and heat distribution markets: An mpec approach
A mathematic program with equilibrium constraints (MPEC) model is proposed to study the strategic behaviors of a profit-driven energy hub in the electricity market and heating market under the background of energy system integration.
Image Registration Based Flicker Solving in Video Face Replacement and Analysis Based Sub-pixel Image Registration
In this paper, a framework of video face replacement is proposed and it deals with the flicker of swapped face in video sequence.
A Goal-oriented Neural Conversation Model by Self-Play
One challenge in applying such techniques to building goal-oriented conversation models is that maximum likelihood-based models are not optimized toward accomplishing goals.
Thoracic Disease Identification and Localization with Limited Supervision
Accurate identification and localization of abnormalities from radiology images play an integral part in clinical diagnosis and treatment planning.
Phase Conductor on Multi-layered Attentions for Machine Comprehension
Attention models have been intensively studied to improve NLP tasks such as machine comprehension via both question-aware passage attention model and self-matching attention model.
Ranked #31 on
Question Answering
on SQuAD1.1 dev
Should We Encode Rain Streaks in Video as Deterministic or Stochastic?
Videos taken in the wild sometimes contain unexpected rain streaks, which brings difficulty in subsequent video processing tasks.
Efficient Online Inference for Infinite Evolutionary Cluster models with Applications to Latent Social Event Discovery
The Recurrent Chinese Restaurant Process (RCRP) is a powerful statistical method for modeling evolving clusters in large scale social media data.
Beyond Low Rank: A Data-Adaptive Tensor Completion Method
The prior for the non-low-rank structure is established based on a mixture of Gaussians which is shown to be flexible enough, and powerful enough, to inform the completion process for a variety of real tensor data.
When Unsupervised Domain Adaptation Meets Tensor Representations
Domain adaption (DA) allows machine learning methods trained on data sampled from one distribution to be applied to data sampled from another.
Learning to Identify Ambiguous and Misleading News Headlines
For the identification of misleading headlines, we extract features based on the congruence between headlines and bodies.
Structural Embedding of Syntactic Trees for Machine Comprehension
Deep neural networks for machine comprehension typically utilizes only word or character embeddings without explicitly taking advantage of structured linguistic information such as constituency trees and dependency trees.
Ranked #40 on
Question Answering
on SQuAD1.1 dev
A Probabilistic Framework for Location Inference from Social Media
In this paper, we formalize the problem of inferring location from social media into a semi-supervised factor graph model (SSFGM).
Pairwise Matching Through Max-Weight Bipartite Belief Propagation
Feature matching is a key problem in computer vision and pattern recognition.
Hyperspectral Compressive Sensing Using Manifold-Structured Sparsity Prior
To reconstruct hyperspectral image (HSI) accurately from a few noisy compressive measurements, we present a novel manifold-structured sparsity prior based hyperspectral compressive sensing (HCS) method in this study.
Reweighted Laplace Prior Based Hyperspectral Compressive Sensing for Unknown Sparsity
To address this problem, a novel reweighted Laplace prior based hyperspectral compressive sensing method is proposed in this study.