Search Results for author:
Found 120 papers, 38 papers with code
Utilizing Cross-Modal Contrastive Learning to Improve Item Categorization BERT Model
Moreover, the proposed method is able to keep using existing text-only IC inference implementation and shows a resource advantage than the deployment of a dual-input MIC system.
A Progressive Framework for Role-Aware Rumor Resolution
Existing works on rumor resolution have shown great potential in recognizing word appearance and user participation.
RIT Boston at SemEval-2022 Task 5: Multimedia Misogyny Detection By Using Coherent Visual and Language Features from CLIP Model and Data-centric AI Principle
Detecting MEME images to be misogynous or not is an application useful on curbing online hateful information against women.
Automatically Detecting Reduced-formed English Pronunciations by Using Deep Learning
Reduced form pronunciations are widely used by native English speakers, especially in casual conversations.
Multimodal Item Categorization Fully Based on Transformer
The Transformer has proven to be a powerful feature extraction method and has gained widespread adoption in natural language processing (NLP).
Retrieval-based Disentanglement with Distant Supervision
Disentangled representation learning remains challenging as ground truth factors of variation do not naturally exist.
Distributed Graph Neural Network Training: A Survey
In this survey, we analyze three major challenges in distributed GNN training that are massive feature communication, the loss of model accuracy and workload imbalance.
Tenrec: A Large-scale Multipurpose Benchmark Dataset for Recommender Systems
Existing benchmark datasets for recommender systems (RS) either are created at a small scale or involve very limited forms of user feedback.
MSRL: Distributed Reinforcement Learning with Dataflow Fragments
Yet, current distributed RL systems tie the definition of RL algorithms to their distributed execution: they hard-code particular distribution strategies and only accelerate specific parts of the computation (e. g. policy network updates) on GPU workers.
A Comprehensive Survey on Trustworthy Recommender Systems
As one of the most successful AI-powered applications, recommender systems aim to help people make appropriate decisions in an effective and efficient way, by providing personalized suggestions in many aspects of our lives, especially for various human-oriented online services such as e-commerce platforms and social media sites.
Scene Text Recognition with Single-Point Decoding Network
In this paper, we propose an efficient attention-free Single-Point Decoding Network (dubbed SPDN) for scene text recognition, which can replace the traditional attention-based decoding network.
Arbitrary Shape Text Detection via Segmentation with Probability Maps
To be concrete, we adopt a Sigmoid Alpha Function (SAF) to transfer the distances between boundaries and their inside pixels to a probability map.
Tower Bridge Net (TB-Net): Bidirectional Knowledge Graph Aware Embedding Propagation for Explainable Recommender Systems
Recently, neural networks based models have been widely used for recommender systems (RS).
Modeling mandatory and discretionary lane changes using dynamic interaction networks
A quantitative understanding of dynamic lane-changing (LC) interaction patterns is indispensable for improving the decision-making of autonomous vehicles, especially in mixed traffic with human-driven vehicles.
A Universal PINNs Method for Solving Partial Differential Equations with a Point Source
In recent years, deep learning technology has been used to solve partial differential equations (PDEs), among which the physics-informed neural networks (PINNs)method emerges to be a promising method for solving both forward and inverse PDE problems.
Time-aware Dynamic Graph Embedding for Asynchronous Structural Evolution
Meanwhile, we treat each edge sequence as a whole and embed its ToV of the first vertex to further encode the time-sensitive information.
DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection
Since GAD emphasizes the application and the rarity of anomalous samples, enriching the varieties of its datasets is a fundamental work.
PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction
We provide in addition the benchmark training procedure for SOTA protein structure prediction model on this dataset.
On Gradient Descent Convergence beyond the Edge of Stability
Gradient Descent (GD) is a powerful workhorse of modern machine learning thanks to its scalability and efficiency in high-dimensional spaces.
SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation
We also compare four categories of perturbation methods for ensemble forecasting, i. e. fixed distribution perturbation, learned distribution perturbation, MC dropout, and multi model ensemble.
MATrIX -- Modality-Aware Transformer for Information eXtraction
In these, text semantics and visual information supplement each other to provide a global understanding of the document.
SideRT: A Real-time Pure Transformer Architecture for Single Image Depth Estimation
To the best of our knowledge, this is the first work to show that transformer-based networks can attain state-of-the-art performance in real-time in the single image depth estimation field.
Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering
While conventional CF models are known for facing the challenges of the popularity bias that favors popular items, one may wonder "Whether the existing graph-based CF models alleviate or exacerbate popularity bias of recommender systems?"
Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos
The generated text prompts are paired with corresponding video clips, and together co-train the text encoder and the video encoder via a contrastive approach.
Ranked #2 on
Action Segmentation
on GTEA
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering
To alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR).
KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models
However, to figure out whether PLMs can be reliable knowledge sources and used as alternative knowledge bases (KBs), we need to further explore some critical features of PLMs.
A Data-Driven Column Generation Algorithm For Bin Packing Problem in Manufacturing Industry
The bin packing problem exists widely in real logistic scenarios (e. g., packing pipeline, express delivery), with its goal to improve the packing efficiency and reduce the transportation cost.
GridTuner: Reinvestigate Grid Size Selection for Spatiotemporal Prediction Models [Technical Report]
In this paper, we study a region partitioning problem, namely optimal grid size selection problem (OGSS), which aims to minimize the real error of spatiotemporal prediction models by selecting the optimal grid size.
An Adaptive Graph Pre-training Framework for Localized Collaborative Filtering
Thus, graph pre-training has the great potential to alleviate data sparsity in GNN-based recommendations.
AutoGEL: An Automated Graph Neural Network with Explicit Link Information
However, existing AutoGNN works mainly adopt an implicit way to model and leverage the link information in the graphs, which is not well regularized to the link prediction task on graphs, and limits the performance of AutoGNN for other graph tasks.
Meta-Auto-Decoder for Solving Parametric Partial Differential Equations
Many important problems in science and engineering require solving the so-called parametric partial differential equations (PDEs), i. e., PDEs with different physical parameters, boundary conditions, shapes of computation domains, etc.
Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters
Specifically, in order to ensure both the training efficiency and the training accuracy, we design a novel hybrid training algorithm, where the embedding layer and the dense neural network are handled by different synchronization mechanisms; then we build a system called Persia (short for parallel recommendation training system with hybrid acceleration) to support this hybrid training algorithm.
Solving Partial Differential Equations with Point Source Based on Physics-Informed Neural Networks
In recent years, deep learning technology has been used to solve partial differential equations (PDEs), among which the physics-informed neural networks (PINNs) emerges to be a promising method for solving both forward and inverse PDE problems.
MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data
Time series forecasting is widely used in business intelligence, e. g., forecast stock market price, sales, and help the analysis of data trend.
Towards More Effective and Economic Sparsely-Activated Model
To increase the number of activated experts without an increase in computational cost, we propose SAM (Switch and Mixture) routing, an efficient hierarchical routing mechanism that activates multiple experts in a same device (GPU).
Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression
To maintain real-time processing in embedded systems, large on-chip memory is required to buffer the interlayer feature maps.
Message Function Search for Hyper-relational Knowledge Graph
In this paper, we first unify a search space of message functions that enables both structures and operators to be searchable.
Outdoor Position Recovery from HeterogeneousTelco Cellular Data
The HMM approaches typically assume stable mobility patterns of the underlying mobile devices.
Fine-Grained Element Identification in Complaint Text of Internet Fraud
Existing system dealing with online complaint provides a final decision without explanations.
An Experimental Study of Quantitative Evaluations on Saliency Methods
It has been long debated that eXplainable AI (XAI) is an important technology for model and data exploration, validation, and debugging.
Align Voting Behavior with Public Statements for Legislator Representation Learning
In addition, we propose a novel task, namely hashtag usage prediction to model the ideology of legislators on Twitter.
Resisting Out-of-Distribution Data Problem in Perturbation of XAI
Besides, our solution also resolves a fundamental problem with the faithfulness indicator, a commonly used evaluation metric of XAI algorithms that appears to be sensitive to the OoD issue.
A Queueing-Theoretic Framework for Vehicle Dispatching in Dynamic Car-Hailing [technical report]
In this paper, we consider an important dynamic car-hailing problem, namely \textit{maximum revenue vehicle dispatching} (MRVD), in which rider requests dynamically arrive and drivers need to serve as many riders as possible such that the entire revenue of the platform is maximized.
Scene-adaptive Knowledge Distillation for Sequential Recommendation via Differentiable Architecture Search
To realize such a goal, we propose AdaRec, a knowledge distillation (KD) framework which compresses knowledge of a teacher model into a student model adaptively according to its recommendation scene by using differentiable Neural Architecture Search (NAS).
Answer Complex Questions: Path Ranker Is All You Need
Currently, the most popular method for open-domain Question Answering (QA) adopts "Retriever and Reader" pipeline, where the retriever extracts a list of candidate documents from a large set of documents followed by a ranker to rank the most relevant documents and the reader extracts answer from the candidates.
Hyper-LifelongGAN: Scalable Lifelong Learning for Image Conditioned Generation
Deep neural networks are susceptible to catastrophic forgetting: when encountering a new task, they can only remember the new task and fail to preserve its ability to accomplish previously learned tasks.
User-specific Adaptive Fine-tuning for Cross-domain Recommendations
Fine-tuning works as an effective transfer learning technique for this objective, which adapts the parameters of a pre-trained model from the source domain to the target domain.
Learning-Aided Heuristics Design for Storage System
Computer systems such as storage systems normally require transparent white-box algorithms that are interpretable for human experts.
Label-Guided Learning for Item Categorization in e-Commerce
Item categorization is an important application of text classification in e-commerce due to its impact on the online shopping experience of users.
THOR, Trace-based Hardware-adaptive layer-ORiented Natural Gradient Descent Computation
It is well-known that second-order optimizer can accelerate the training of deep neural networks, however, the huge computation cost of second-order optimization makes it impractical to apply in real practice.
Set2setRank: Collaborative Set to Set Ranking for Implicit Feedback based Recommendation
Despite the performance gain of these implicit feedback based models, the recommendation results are still far from satisfactory due to the sparsity of the observed item set for each user.
MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
Spatio-temporal action detection is an important and challenging problem in video understanding.
Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation
In contrast, we propose a parameter efficient framework, Piggyback GAN, which learns the current task by building a set of convolutional and deconvolutional filters that are factorized into filters of the models trained on previous tasks.
Adaptive Appearance Rendering
Hence, we develop an approach based on intermediate representations of poses and appearance: our pose-guided appearance rendering network firstly encodes the targets' poses using an encoder-decoder neural network.
Efficient Relation-aware Scoring Function Search for Knowledge Graph Embedding
The scoring function, which measures the plausibility of triplets in knowledge graphs (KGs), is the key to ensure the excellent performance of KG embedding, and its design is also an important problem in the literature.
Searching to Sparsify Tensor Decomposition for N-ary Relational Data
Recently, tensor decomposition methods have been introduced into N-ary relational data and become state-of-the-art on embedding learning.
ZYELL-NCTU NetTraffic-1.0: A Large-Scale Dataset for Real-World Network Anomaly Detection
Network security has been an active research topic for long.
Learning Fair Representations for Recommendation: A Graph-based Perspective
For each user, this transformation is achieved under the adversarial learning of a user-centric graph, in order to obfuscate each sensitive feature between both the filtered user embedding and the sub graph structures of this user.
Field-free spin-orbit torque-induced switching of perpendicular magnetization in a ferrimagnetic layer with vertical composition gradient
Existing methods to do so involve the application of an in-plane bias magnetic field, or incorporation of in-plane structural asymmetry in the device, both of which can be difficult to implement in practical applications.
Mesoscale and Nanoscale Physics
Far-Field Super-Resolution Imaging By Nonlinear Excited Evanescent Waves
Abbe's resolution limit, one of the best-known physical limitations, poses a great challenge for any wave systems in imaging, wave transport, and dynamics.
Super-Resolution
Optics
FTSO: Effective NAS via First Topology Second Operator
Existing one-shot neural architecture search (NAS) methods generally contain a giant supernet, which leads to heavy computational costs.
EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo
As a result, we achieve promising results on all datasets and the highest F-Score on the online TNT intermediate benchmark.
Ranked #2 on
Point Clouds
on Tanks and Temples
Quantitative Evaluations on Saliency Methods: An Experimental Study
It has been long debated that eXplainable AI (XAI) is an important topic, but it lacks rigorous definition and fair metrics.
Modeling Evolution of Message Interaction for Rumor Resolution
Previous work for rumor resolution concentrates on exploiting time-series characteristics or modeling topology structure separately.
PG-GSQL: Pointer-Generator Network with Guide Decoding for Cross-Domain Context-Dependent Text-to-SQL Generation
We pay close attention to the cross-domain context-dependent text-to-SQL generation task, which requires a model to depend on the interaction history and current utterance to generate SQL query.
Scalable Federated Learning over Passive Optical Networks
Two-step aggregation is introduced to facilitate scalable federated learning (SFL) over passive optical networks (PONs).
Networking and Internet Architecture
On Graph Neural Networks versus Graph-Augmented MLPs
From the perspective of expressive power, this work compares multi-layer Graph Neural Networks (GNNs) with a simplified alternative that we call Graph-Augmented Multi-Layer Perceptrons (GA-MLPs), which first augments node features with certain multi-hop operators on the graph and then applies an MLP in a node-wise fashion.
Efficient, Simple and Automated Negative Sampling for Knowledge Graph Embedding
In this paper, motivated by the observation that negative triplets with large gradients are important but rare, we propose to directly keep track of them with the cache.
UniNet: Scalable Network Representation Learning with Metropolis-Hastings Sampling
Finally, with the new edge sampler and random walk model abstraction, we carefully implement a scalable NRL framework called UniNet.
Improving Sequential Latent Variable Models with Autoregressive Flows
We propose an approach for improving sequence modeling based on autoregressive normalizing flows.
Semi-Anchored Detector for One-Stage Object Detection
The anchor-free strategy benefits the classification task but can lead to sup-optimum for the regression task due to the lack of prior bounding boxes.
SPL-MLL: Selecting Predictable Landmarks for Multi-Label Learning
Although significant progress achieved, multi-label classification is still challenging due to the complexity of correlations among different labels.
Learning to Transfer Graph Embeddings for Inductive Graph based Recommendation
The transfer network is designed to approximate the learned item embeddings from graph neural networks by taking each item's visual content as input, in order to tackle the new segment problem in the test phase.
Noise-Sampling Cross Entropy Loss: Improving Disparity Regression Via Cost Volume Aware Regularizer
Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance.
Multi-View Self-Attention for Interpretable Drug-Target Interaction Prediction
In this study, we propose a self-attention-based multi-view representation learning approach for modeling drug-target interactions.
STAS: Adaptive Selecting Spatio-Temporal Deep Features for Improving Bias Correction on Precipitation
We thus propose an end-to-end deep-learning BCoP model named Spatio-Temporal feature Auto-Selective (STAS) model to select optimal ST regularity from EC via the ST Feature-selective Mechanisms (SFM/TFM).
Consistent and Complementary Graph Regularized Multi-view Subspace Clustering
The complementary graph regularizer investigates the specific information of multiple views.
U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation
This paper proposes a novel U-Net variant using stacked dilated convolutions for medical image segmentation (SDU-Net).
Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting
This work proposes a novel approach for multiple time series forecasting.
Can Graph Neural Networks Count Substructures?
We also prove positive results for k-WL and k-IGNs as well as negative results for k-WL with a finite number of iterations.
Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach
Second, we propose a residual network structure that is specifically designed for CF with user-item interaction modeling, which alleviates the over smoothing problem in graph convolution aggregation operation with sparse user-item interaction data.
Adapting Grad-CAM for Embedding Networks
Then, we develop an efficient weight-transfer method to explain decisions for any image without back-propagation.
Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding
In this work, based on the relational paths, which are composed of a sequence of triplets, we define the Interstellar as a recurrent neural architecture search problem for the short-term and long-term information along the paths.
SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator
Intrinsic graph convolution operators with differentiable kernel functions play a crucial role in analyzing 3D shape meshes.
A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) has attracted increasing attention recently due to its broad applications.
Ranked #3 on
Aspect-Based Sentiment Analysis
on MAMS
Bandwidth Slicing to Boost Federated Learning in Edge Computing
Bandwidth slicing is introduced to support federated learning in edge computing to assure low communication delay for training traffic.
Towards a Precipitation Bias Corrector against Noise and Maldistribution
To the best of our knowledge, it is the first expert-free models for bias correction.
DR Loss: Improving Object Detection by Distributional Ranking
This architecture is efficient but can suffer from the imbalance issue with respect to two aspects: the inter-class imbalance between the number of candidates from foreground and background classes and the intra-class imbalance in the hardness of background candidates, where only a few candidates are hard to be identified.
Lifelong GAN: Continual Learning for Conditional Image Generation
This makes it possible to perform image-conditioned generation tasks in a lifelong learning setting.
Precipitation Nowcasting with Star-Bridge Networks
Precipitation nowcasting, which aims to precisely predict the short-term rainfall intensity of a local region, is gaining increasing attention in the artificial intelligence community.
Personalized Multimedia Item and Key Frame Recommendation
We argue that the key challenge of this problem lies in discovering users' visual profiles for key frame recommendation, as most recommendation models would fail without any users' fine-grained image behavior.
On the equivalence between graph isomorphism testing and function approximation with GNNs
Graph neural networks (GNNs) have achieved lots of success on graph-structured data.
Ranked #21 on
Graph Regression
on ZINC-500k
AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
The algorithm is further sped up by a filter and a predictor, which can avoid repeatedly training SFs with same expressive ability and help removing bad candidates during the search before model training.
Ranked #1 on
Link Prediction
on FB15k
Universal chosen-ciphertext attack for a family of image encryption schemes
During the past decades, there is a great popularity employing nonlinear dynamics and permutation-substitution architecture for image encryption.
Multimedia
Quality-aware Unpaired Image-to-Image Translation
To tackle the above two challenges, in this paper, we propose a unified quality-aware GAN-based framework for unpaired image-to-image translation, where a quality-aware loss is explicitly incorporated by comparing each source image and the reconstructed image at the domain level.
NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding
Negative sampling, which samples negative triplets from non-observed ones in the training data, is an important step in KG embedding.
Ranked #5 on
Link Prediction
on FB15k
Local Distribution in Neighborhood for Classification
Additionally, based on the local distribution, we generate a generalized local classification form that can be effectively applied to various datasets through tuning the parameters.
Application of Deep Learning on Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations
We explore how Deep Learning (DL) can be utilized to predict prognosis of acute myeloid leukemia (AML).
Part-Activated Deep Reinforcement Learning for Action Prediction
In this paper, we propose a part-activated deep reinforcement learning (PA-DRL) for action prediction.
A Hierarchical Attention Model for Social Contextual Image Recommendation
After that, we design a hierarchical attention network that naturally mirrors the hierarchical relationship (elements in each aspects level, and the aspect level) of users' latent interests with the identified key aspects.
Proteomics Analysis of FLT3-ITD Mutation in Acute Myeloid Leukemia Using Deep Learning Neural Network
The results of this study allow a novel approach to determine critical protein pathways in the FLT3-ITD mutation, and provide proof-of-concept for an accurate approach to model big data in cancer proteomics and genomics.
Learning to Forecast Videos of Human Activity with Multi-granularity Models and Adaptive Rendering
An architecture combining a hierarchical temporal model for predicting human poses and encoder-decoder convolutional neural networks for rendering target appearances is proposed.
Multi-view Registration Based on Weighted Low Rank and Sparse Matrix Decomposition of Motions
Then, it proposes the weighted LRS decomposition, where each block element is assigned with one estimated weight to denote its reliability.
Predicting Audience's Laughter During Presentations Using Convolutional Neural Network
Public speakings play important roles in schools and work places and properly using humor contributes to effective presentations.
Subjective Knowledge Acquisition and Enrichment Powered By Crowdsourcing
In our work, we propose a system, called crowdsourced subjective knowledge acquisition (CoSKA), for subjective knowledge acquisition powered by crowdsourcing and existing KBs.
Predicting Audience's Laughter Using Convolutional Neural Network
For the purpose of automatically evaluating speakers' humor usage, we build a presentation corpus containing humorous utterances based on TED talks.
Can We Make Computers Laugh at Talks?
Considering the importance of public speech skills, a system which makes a prediction on where audiences laugh in a talk can be helpful to a person who prepares for a talk.
Zero-Shot Learning with Multi-Battery Factor Analysis
Zero-shot learning (ZSL) extends the conventional image classification technique to a more challenging situation where the test image categories are not seen in the training samples.
Analyzing Time Series Changes of Correlation between Market Share and Concerns on Companies measured through Search Engine Suggests
We finally propose how to predict the market share of a specific product genre based on the rates of concerns of those who search for Web pages.
Deep Structured Models For Group Activity Recognition
This paper presents a deep neural-network-based hierarchical graphical model for individual and group activity recognition in surveillance scenes.
Is getting the right answer just about choosing the right words? The role of syntactically-informed features in short answer scoring
Developments in the educational landscape have spurred greater interest in the problem of automatically scoring short answer questions.
