Search Results for author:
Found 148 papers, 51 papers with code
Sparse Shrunk Additive Models
Meanwhile, in these feature selection models, the interactions between features are often ignored or just discussed under prior structure information.
Improving Privacy Guarantee and Efficiency of Latent Dirichlet Allocation Model Training Under Differential Privacy
To improve the privacy guarantee and efficiency, we combine a subsampling method with CGS and propose a novel LDA training algorithm with differential privacy, SUB-LDA.
P-INT: A Path-based Interaction Model for Few-shot Knowledge Graph Completion
Its general process is to first encode the implicit relation of an entity pair and then match the relation of a query entity pair with the relations of the reference entity pairs.
A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base
Knowledge Base Question Answering (KBQA) is to answer natural language questions posed over knowledge bases (KBs).
FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management
FlowKV's core innovation is a multi-turn isolation mechanism that preserves the accumulated compressed KV cache from past turns.
Unsupervised Learning for Class Distribution Mismatch
Specifically, with a 60% mismatch proportion on Tiny-ImageNet dataset, our approach, without relying on labeled data, surpasses OpenMatch (with 40 labels per class) by 35. 1%, 63. 7%, and 72. 5% in classifying known, unknown, and new classes.
Modular-Cam: Modular Dynamic Camera-view Video Generation with LLM
To generate a video containing dynamic scenes that match the given camera-views, we incorporate the widely-used temporal transformer into the diffusion model to ensure continuity within a single scene and propose CamOperator, a modular network based module that well controls the camera movements.
QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition
Large Language Models (LLMs) excel in diverse applications but suffer inefficiency due to massive scale.
RAD: Retrieval-Augmented Decision-Making of Meta-Actions with Vision-Language Models in Autonomous Driving
Additionally, we fine-tune VLMs on a specifically curated dataset derived from the NuScenes dataset to enhance their spatial perception and bird's-eye view image comprehension capabilities.
Behavior Importance-Aware Graph Neural Architecture Search for Cross-Domain Recommendation
To the best of our knowledge, this is the first work to jointly optimize GNN architecture and behavior data importance for cross-domain recommendation.
LLMIdxAdvis: Resource-Efficient Index Advisor Utilizing Large Language Model
Index recommendation is essential for improving query performance in database management systems (DBMSs) through creating an optimal set of indexes under specific constraints.
OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale
Text-to-SQL, the task of translating natural language questions into SQL queries, plays a crucial role in enabling non-experts to interact with databases.
The Noisy Path from Source to Citation: Measuring How Scholars Engage with Past Research
Using a quasi-experiment, we establish the "telephone effect" - when citing papers have low fidelity to the original claim, future papers that cite the citing paper and the original have lower fidelity to the original.
HRR: Hierarchical Retrospection Refinement for Generated Image Detection
However, existing methods primarily focused on detecting a specific generative model and emphasizing the localization of synthetic regions, while neglecting the interference caused by image size and style on model learning.
Co-MTP: A Cooperative Trajectory Prediction Framework with Multi-Temporal Fusion for Autonomous Driving
In this paper, we introduce the Co-MTP, a general cooperative trajectory prediction framework with multi-temporal fusion for autonomous driving, which leverages the V2X system to fully capture the interaction among agents in both history and future domains to benefit the planning.
Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
Privacy tokens encapsulate gradient features and, when combined with data features, offer valuable insights into the extent of private information leakage from training data, enabling real-time measurement of privacy risks without relying on adversarial attack simulations.
Can LLMs Maintain Fundamental Abilities under KV Cache Compression?
This paper investigates an underexplored challenge in large language models (LLMs): the impact of KV cache compression methods on LLMs' fundamental capabilities.
LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model
Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity.
Knowledge Sharing-enabled Semantic Rate Maximization for Multi-cell Task-oriented Hybrid Semantic-Bit Communication Networks
The traditional bit communications can be adopted as an aid to transmit the rest data related to unshared mismatched knowledge to guarantee the effective execution of target tasks.
Collaborative Knowledge Sharing-empowered Effective Semantic Rate Maximization for Two-tier Semantic-Bit Communication Networks
Effective task-oriented semantic communications relies on perfect knowledge alignment between transmitters and receivers for accurate recovery of task-related semantic information, which can be susceptible to knowledge misalignment and performance degradation in practice.
Personalized Clustering via Targeted Representation Learning
In this paper, we propose a personalized clustering method that explicitly performs targeted representation learning by interacting with users via modicum task information (e. g., $\textit{must-link}$ or $\textit{cannot-link}$ pairs) to guide the clustering direction.
RAC3: Retrieval-Augmented Corner Case Comprehension for Autonomous Driving with Vision-Language Models
We evaluate RAC3 through extensive experiments using a curated dataset of corner case scenarios, demonstrating its ability to enhance semantic alignment, improve hallucination mitigation, and achieve superior performance metrics, such as Cosine Similarity and ROUGE-L scores.
TSGaussian: Semantic and Depth-Guided Target-Specific Gaussian Splatting from Sparse Views
Recent advances in Gaussian Splatting have significantly advanced the field, achieving both panoptic and interactive segmentation of 3D scenes.
SAM Decoding: Speculative Decoding via Suffix Automaton
Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration.
P$^2$ Law: Scaling Law for Post-Training After Model Pruning
Pruning has become a widely adopted technique for reducing the hardware requirements of large language models (LLMs).
Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoising
We investigate the construction of gradient-guided conditional diffusion models for reconstructing private images, focusing on the adversarial interplay between differential privacy noise and the denoising capabilities of diffusion models.
VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
In this paper, we propose a more challenging fine-grained VCMR benchmark requiring methods to localize the best-matched moment from the corpus with other partially matched candidates.
Generalized Sparse Additive Model with Unknown Link Function
The proposed GSAMUL can realize both variable selection and hidden interaction.
PCQPR: Proactive Conversational Question Planning with Reflection
Conversational Question Generation (CQG) enhances the interactivity of conversational question-answering systems in fields such as education, customer service, and entertainment.
Multi-Modal Generative AI: Multi-modal LLM, Diffusion and Beyond
Particularly, two dominant families of techniques are: i) The multi-modal large language model (MLLM) such as GPT-4V, which shows impressive ability for multi-modal understanding; ii) The diffusion model such as Sora, which exhibits remarkable multi-modal powers, especially with respect to visual generation.
A Safe Self-evolution Algorithm for Autonomous Driving Based on Data-Driven Risk Quantification Model
The results show that the proposed algorithm can generate safe and reasonable actions in a variety of complex scenarios and guarantee safety without losing the evolutionary potential of learning-based autonomous driving systems.
A Safe and Efficient Self-evolving Algorithm for Decision-making and Control of Autonomous Driving Systems
Autonomous vehicles with a self-evolving ability are expected to cope with unknown scenarios in the real-world environment.
Minor SFT loss for LLM fine-tune to increase performance and reduce model deviation
Instruct LLM provide a paradigm used in large scale language model to align LLM to human preference.
Minor DPO reject penalty to increase training robustness
In the past it uses reinforcement learning from human feedback (RLHF) algorithm to optimize the LLM policy to align with these preferences and not to draft too far from the original model.
A Population-to-individual Tuning Framework for Adapting Pretrained LM to On-device User Intent Prediction
Mobile devices, especially smartphones, can support rich functions and have developed into indispensable tools in daily life.
Is Large Language Model Good at Database Knob Tuning? A Comprehensive Experimental Evaluation
Knob tuning plays a crucial role in optimizing databases by adjusting knobs to enhance database performance.
Unleash the Power of Ellipsis: Accuracy-enhanced Sparse Vector Technique with Exponential Noise
To provide a rigorous DP guarantee for SVT, prior works in the literature adopt a conservative privacy analysis by assuming the direct disclosure of noisy query results as in typical private query releases.
Multi-sentence Video Grounding for Long Video Generation
(iii) We also attempt video morphing and personalized generation methods to improve the subject consistency of long video generation, providing ablation experimental results for the subtasks of long video generation.
QVD: Post-training Quantization for Video Diffusion Models
Furthermore, we investigate significant inter-channel disparities and asymmetries in the activation of video diffusion models, resulting in low coverage of quantization levels by individual channels and increasing the challenge of quantization.
PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods
In domain-specific applications, GPT-4, augmented with precise prompts or Retrieval-Augmented Generation (RAG), shows notable potential but faces the critical tri-lemma of performance, cost, and data privacy.
A Learn-Then-Reason Model Towards Generalization in Knowledge Base Question Answering
In order to improve the generalization capabilities of KBQA models, extensive research has embraced a retrieve-then-reason framework to retrieve relevant evidence for logical expression generation.
How Does Distribution Matching Help Domain Generalization: An Information-theoretic Analysis
Domain generalization aims to learn invariance across multiple training domains, thereby enhancing generalization against out-of-distribution data.
Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model
Gradient leakage has been identified as a potential source of privacy breaches in modern image processing systems, where the adversary can completely reconstruct the training images from leaked gradients.
DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning
Third, the model is updated with the gradient reconstructed from recycled common knowledge and noisy incremental information.
Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails
However, recent studies have shown that the gradients in deep learning exhibit a heavy-tail phenomenon, that is, the tails of the gradient have infinite variance, which may lead to excessive clipping loss to the gradients with existing DPSGD mechanisms.
DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control
To tackle the problems, in this paper, we propose DisenStudio, a novel framework that can generate text-guided videos for customized multiple subjects, given few images for each subject.
PTQ4SAM: Post-Training Quantization for Segment Anything
We analyze its characteristics from both per-tensor and per-channel perspectives, and propose a Bimodal Integration strategy, which utilizes a mathematically equivalent sign operation to transform the bimodal distribution into a relatively easy-quantized normal distribution offline.
An empirical study of LLaMA3 quantization: from LLMs to MLLMs
To uncover the capabilities of low-bit quantized MLLM, we assessed the performance of the LLaMA3-based LLaVA-Next-8B model under 2-4 ultra-low bits with post-training quantization methods.
Sample Design Engineering: An Empirical Study of What Makes Good Downstream Fine-Tuning Samples for LLMs
In the burgeoning field of Large Language Models (LLMs) like ChatGPT and LLaMA, Prompt Engineering (PE) is renowned for boosting zero-shot or in-context learning (ICL) through prompt modifications.
E2ETune: End-to-End Knob Tuning via Fine-tuned Generative Language Model
Database knob tuning is a significant challenge for database administrators, as it involves tuning a large number of configuration knobs with continuous or discrete values to achieve optimal database performance.
TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding
The image overview stage provides a comprehensive understanding of the global scene information, and the coarse localization stage approximates the image area containing the answer based on the question asked.
SGSH: Stimulate Large Language Models with Skeleton Heuristics for Knowledge Base Question Generation
Knowledge base question generation (KBQG) aims to generate natural language questions from a set of triplet facts extracted from KB.
Negative Label Guided OOD Detection with Pretrained Vision-Language Models
In this paper, we propose a novel post hoc OOD detection method, called NegLabel, which takes a vast number of negative labels from extensive corpus databases.
Streamlining Redundant Layers to Compress Large Language Models
This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs).
Open-World Semi-Supervised Learning for Node Classification
Open-world semi-supervised learning (Open-world SSL) for node classification, that classifies unlabeled nodes into seen classes or multiple novel classes, is a practical but under-explored problem in the graph community.
Event-Driven Learning for Spiking Neural Networks
Specifically, we introduce two novel event-driven learning methods: the spike-timing-dependent event-driven (STD-ED) and membrane-potential-dependent event-driven (MPD-ED) algorithms.
Online Ecological Gearshift Strategy via Neural Network with Soft-Argmax Operator
This paper presents a neural network optimizer with soft-argmax operator to achieve an ecological gearshift strategy in real-time.
CodeS: Towards Building Open-source Language Models for Text-to-SQL
To address the limitations, we introduce CodeS, a series of pre-trained language models with parameters ranging from 1B to 15B, specifically designed for the text-to-SQL task.
Evolutionary Reinforcement Learning: A Systematic Review and Future Directions
In response to the limitations of reinforcement learning and evolutionary algorithms (EAs) in complex problem-solving, Evolutionary Reinforcement Learning (EvoRL) has emerged as a synergistic solution.
DB-LLM: Accurate Dual-Binarization for Efficient LLMs
Large language models (LLMs) have significantly advanced the field of natural language processing, while the expensive memory and computation consumption impede their practical deployment.
Spiking-PhysFormer: Camera-Based Remote Photoplethysmography with Parallel Spike-driven Transformer
Additionally, the power consumption of the transformer block is reduced by a factor of 12. 2, while maintaining decent performance as PhysFormer and other ANN-based models.
Dynamic Cues-Assisted Transformer for Robust Point Cloud Registration
Point Cloud Registration is a critical and challenging task in computer vision.
Grounding-Prompter: Prompting LLM with Multimodal Information for Temporal Sentence Grounding in Long Videos
To tackle these challenges, in this work we propose a Grounding-Prompter method, which is capable of conducting TSG in long videos through prompting LLM with multimodal information.
LLM4VG: Large Language Models Evaluation for Video Grounding
Recently, researchers have attempted to investigate the capability of LLMs in handling videos and proposed several video LLM models.
FOSS: A Self-Learned Doctor for Query Optimizer
They either learn to construct plans from scratch in a bottom-up manner or steer the plan generation behavior of traditional optimizer using hints.
Prospective Role of Foundation Models in Advancing Autonomous Vehicles
With the development of artificial intelligence and breakthroughs in deep learning, large-scale Foundation Models (FMs), such as GPT, Sora, etc., have achieved remarkable results in many fields including natural language processing and computer vision.
PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance
We prove that pre-projection enhances the convergence of DP-SGD by reducing the dependence of clipping error and bias to a fraction of the top gradient eigenspace, and in theory, limits cross-client variance to improve the convergence under heterogeneous federation.
VTimeLLM: Empower LLM to Grasp Video Moments
Large language models (LLMs) have shown remarkable text understanding capabilities, which have been extended as Video LLMs to handle video data for comprehending visual details.
Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing
In this paper, we propose a novel post-training quantization method PCR (Progressive Calibration and Relaxing) for text-to-image diffusion models, which consists of a progressive calibration strategy that considers the accumulated quantization error across timesteps, and an activation relaxing strategy that improves the performance with negligible cost.
Lightweight Diffusion Models with Distillation-Based Block Neural Architecture Search
When retraining the searched architecture, we adopt a dynamic joint loss to maintain the consistency between supernet training and subnet retraining, which also provides informative objectives for each block and shortens the paths of gradient propagation.
VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning
The video generator is further customized for the given multiple subjects by the proposed Disen-Mix Finetuning and Human-in-the-Loop Re-finetuning strategy, which can tackle the attribute binding problem of multi-subject generation.
Data-Centric Financial Large Language Models
Large language models (LLMs) show promise for natural language tasks but struggle when applied directly to complex domains like finance.
Adversarial Driving Behavior Generation Incorporating Human Risk Cognition for Autonomous Vehicle Evaluation
Autonomous vehicle (AV) evaluation has been the subject of increased interest in recent years both in industry and in academia.
Diversifying Question Generation over Knowledge Base via External Natural Questions
The above insights make diversifying question generation an intriguing task, where the first challenge is evaluation metrics for diversity.
A Comprehensive Survey on Deep Learning Techniques in Educational Data Mining
With the increasing complexity and diversity of educational data, Deep Learning techniques have shown significant advantages in addressing the challenges associated with analyzing and modeling this data.
SAM-Deblur: Let Segment Anything Boost Image Deblurring
Image deblurring is a critical task in the field of image restoration, aiming to eliminate blurring artifacts.
$\rm SP^3$: Enhancing Structured Pruning via PCA Projection
Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension (d) in PLMs, a dimension critical to model size and efficiency.
A Mobile Data-Driven Hierarchical Deep Reinforcement Learning Approach for Real-time Demand-Responsive Railway Rescheduling and Station Overcrowding Mitigation
The use of MD has enabled the modelling of passenger dynamics in response to train delays and station crowdedness, and a real-time optimisation for rescheduling of train services in view of the change in demand as a result of passengers' behavioural response to disruption.
Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatch
Specifically, WAD captures adaptive weights and high-quality pseudo labels to target instances by exploring point mutual information (PMI) in representation space to maximize the role of unlabeled data and filter unknown categories.
Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks
To fill the gap, we propose a Spiking-Diffusion model, which is based on the vector quantized discrete diffusion model.
Ranked #1 on
Image Generation
on EMNIST-Letters
Exploring Linguistic Style Matching in Online Communities: The Role of Social Context and Conversation Dynamics
Linguistic style matching (LSM) in conversations can be reflective of several aspects of social influence such as power or persuasion.
FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering
The generalization problem on KBQA has drawn considerable attention.
ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer
To mitigate the data scarcity in learning visual acoustic information, we 1) introduce a self-supervised learning framework to enhance both the visual-text encoder and denoiser decoder; 2) leverage the diffusion transformer scalable in terms of parameters and capacity to learn visual scene information.
CageViT: Convolutional Activation Guided Efficient Vision Transformer
Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence.
DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation
To tackle the problems, we propose DisenBooth, an identity-preserving disentangled tuning framework for subject-driven text-to-image generation.
DELTA: Dynamic Embedding Learning with Truncated Conscious Attention for CTR Prediction
To tackle this problem, inspired by the Global Workspace Theory in conscious processing, which posits that only a specific subset of the product features are pertinent while the rest can be noisy and even detrimental to human-click behaviors, we propose a CTR model that enables Dynamic Embedding Learning with Truncated Conscious Attention for CTR prediction, termed DELTA.
Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective
However, the current generalization error bounds within this framework are still far from optimal, while substantial improvements on these bounds are quite challenging due to the intractability of high-dimensional information quantities.
Open-World Social Event Classification
To tackle these challenges, we propose an Open-World Social Event Classifier (OWSEC) model in this paper.
Detecting Out-of-distribution Data through In-distribution Class Prior
In this paper, we show that this assumption makes the above methods incapable when the ID model is trained with class-imbalanced data. Fortunately, by analyzing the causal relations between ID/OOD classes and features, we identify several common scenarios where the OOD-to-ID probabilities should be the ID-class-prior distribution and propose two strategies to modify existing inference-time detection methods: 1) replace the uniform distribution with the ID-class-prior distribution if they explicitly use the uniform distribution; 2) otherwise, reweight their scores according to the similarity between the ID-class-prior distribution and the softmax outputs of the pre-trained model.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Model
In this work, a general framework (APES) is built up to strengthen model privacy under personalized local privacy by leveraging the privacy amplification effect of the shuffle model.
DIRE for Diffusion-Generated Image Detection
We find that existing detectors struggle to detect images generated by diffusion models, even if we include generated images from a specific diffusion model in their training data.
On the Stability and Generalization of Triplet Learning
Triplet learning, i. e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e. g., face recognition and person re-identification.
Stability-based Generalization Analysis for Mixtures of Pointwise and Pairwise Learning
Recently, some mixture algorithms of pointwise and pairwise learning (PPL) have been formulated by employing the hybrid error metric of "pointwise loss + pairwise loss" and have shown empirical effectiveness on feature selection, ranking and recommendation tasks.
RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL
Due to the structural property of the SQL queries, the seq2seq model takes the responsibility of parsing both the schema items (i. e., tables and columns) and the skeleton (i. e., SQL keywords).
Ranked #1 on
Semantic Parsing
on spider
Temporal-Coded Spiking Neural Networks with Dynamic Firing Threshold: Learning with Event-Driven Backpropagation
As a temporal encoding scheme for SNNs, Time-To-First-Spike (TTFS) encodes information using the timing of a single spike, which allows spiking neurons to transmit information through sparse spike trains and results in lower power consumption and higher computational efficiency compared to traditional rate-based encoding counterparts.
Superclass Learning With Representation Enhancement
In many real scenarios, data are often divided into a handful of artificial super categories in terms of expert knowledge rather than the representations of images.
On the Global Solution of Soft k-Means
This paper presents an algorithm to solve the Soft k-Means problem globally.
Robust and Fast Measure of Information via Low-rank Representation
The matrix-based R\'enyi's entropy allows us to directly quantify information measures from given data, without explicit estimation of the underlying probability distribution.
Disentangled Representation Learning
Disentangled Representation Learning (DRL) aims to learn a model capable of identifying and disentangling the underlying factors hidden in the observable data in representation form.
Oracle-guided Contrastive Clustering
Accordingly, the query results, guided by oracles with distinctive demands, may drive the OCC's clustering results in a desired orientation.
StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning
Existing automatic story evaluation methods place a premium on story lexical level coherence, deviating from human preference.
Character-Centric Story Visualization via Visual Planning and Token Alignment
This task requires machines to 1) understand long text inputs and 2) produce a globally consistent image sequence that illustrates the contents of the story.
Global Weighted Tensor Nuclear Norm for Tensor Robust Principal Component Analysis
Tensor Robust Principal Component Analysis (TRPCA), which aims to recover a low-rank tensor corrupted by sparse noise, has attracted much attention in many real applications.
NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results
We present the design and baseline results for a new challenge in the ChaLearn meta-learning series, accepted at NeurIPS'22, focusing on "cross-domain" meta-learning.
Bag of Tricks for Out-of-Distribution Generalization
Recently, out-of-distribution (OOD) generalization has attracted attention to the robustness and generalization ability of deep learning based models, and accordingly, many strategies have been made to address different aspects related to this issue.
AntCritic: Argument Mining for Free-Form and Visually-Rich Financial Comments
Argument mining aims to detect all possible argumentative components and identify their relationships automatically.
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification
Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such resources are available.
Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts
Stories or narratives are comprised of a sequence of events.
PrivateRec: Differentially Private Training and Serving for Federated News Recommendation
Collecting and training over sensitive personal data raise severe privacy concerns in personalized recommendation systems, and federated learning can potentially alleviate the problem by training models over decentralized user data. However, a theoretically private solution in both the training and serving stages of federated recommendation is essential but still lacking. Furthermore, naively applying differential privacy (DP) to the two stages in federated recommendation would fail to achieve a satisfactory trade-off between privacy and utility due to the high-dimensional characteristics of model gradients and hidden representations. In this work, we propose a federated news recommendation method for achieving a better utility in model training and online serving under a DP guarantee. We first clarify the DP definition over behavior data for each round in the life-circle of federated recommendation systems. Next, we propose a privacy-preserving online serving mechanism under this definition based on the idea of decomposing user embeddings with public basic vectors and perturbing the lower-dimensional combination coefficients.
OMG: Observe Multiple Granularities for Natural Language-Based Vehicle Retrieval
For the textual representation, one global embedding, three local embeddings and a color-type prompt embedding are extracted to represent various granularities of semantic features.
NOC-REK: Novel Object Captioning with Retrieved Vocabulary from External Knowledge
We propose an end-to-end Novel Object Captioning with Retrieved vocabulary from External Knowledge method (NOC-REK), which simultaneously learns vocabulary retrieval and caption generation, successfully describing novel objects outside of the training dataset.
Error-based Knockoffs Inference for Controlled Feature Selection
Recently, the scheme of model-X knockoffs was proposed as a promising solution to address controlled feature selection under high-dimensional finite-sample settings.
Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
Recent works on knowledge base question answering (KBQA) retrieve subgraphs for easier reasoning.
No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices
In this way, all the clients can participate in the model learning in FL, and the final model can be big and powerful enough.
Equilibrium Defaultable Corporate Debt and Investment
In dynamic capital structure models with an investor break-even condition, the firm's Bellman equation may not generate a contraction mapping, so the standard existence and uniqueness conditions do not apply.
An Accelerator for Rule Induction in Fuzzy Rough Theory
First, a rule induction method based on consistence degree, called Consistence-based Value Reduction (CVR), is proposed and used as basis to accelerate.
Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models
Embedding-based methods are popular for Knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constrained questions.
Markov subsampling based Huber Criterion
Subsampling is an important technique to tackle the computational challenges brought by big data.
Regularized Modal Regression on Markov-dependent Observations: A Theoretical Assessment
Our results show that the Markov dependence impacts on the generalization error in the way that sample size would be discounted by a multiplicative factor depending on the spectral gap of underlying Markov chain.
Self-supervised Graph Learning for Occasional Group Recommendation
As each occasional group has extremely sparse interactions with items, traditional group recommendation methods can not learn high-quality group representations.
A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation
In terms of the pretext task, in addition to considering the intra-correlations of users and items by the embedding reconstruction task, we add embedding contrastive learning task to capture inter-correlations of users and items.
Curriculum Disentangled Recommendation with Noisy Multi-feedback
However, learning such disentangled representations from multi-feedback data is challenging because i) multi-feedback is complex: there exist complex relations among different types of feedback (e. g., click, unclick, and dislike, etc) as well as various user intentions, and ii) multi-feedback is noisy: there exists noisy (useless) information both in features and labels, which may deteriorate the recommendation performance.
Eco-Coasting Strategies Using Road Grade Preview: Evaluation and Online Implementation Based on Mixed Integer Model Predictive Control
However, the comprehensive comparison between different coasting strategies and online performance of the eco-coasting strategy using road grade preview are still unclear because of the oversimplification and the integer variable in the optimal control problems.
SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation
Generating texts in scientific papers requires not only capturing the content contained within the given input but also frequently acquiring the external information called \textit{context}.
Huber Additive Models for Non-stationary Time Series Analysis
Moreover, the error bound for non-stationary time series contains a discrepancy measure for the shifts of the data distributions over time.
Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling
To enrich the candidate concepts, a commonsense knowledge graph is created for each image sequence from which the concept candidates are proposed.
Ranked #19 on
Visual Storytelling
on VIST
GraphPlan: Story Generation by Planning with Event Graph
In this paper, we focus on planning a sequence of events assisted by event graphs, and use the events to guide the generator.
A Bayesian Federated Learning Framework with Online Laplace Approximation
On the client side, a prior loss that uses the global posterior probabilistic parameters delivered from the server is designed to guide the local training.
Energy cost study for controlling complex social networks with conformity behavior
Therefore, to understand controlling social systems with conformity, discrete-time modelling is used and the energy cost scaling laws are derived.
Physics and Society
Contrastive Coding for Active Learning Under Class Distribution Mismatch
However, its performance deteriorates under class distribution mismatch, wherein the unlabeled data contain many samples out of the class distribution of labeled data.
Recommending Courses in MOOCs for Jobs: An Auto Weak Supervision Approach
On the one hand, the framework enables training multiple supervised ranking models upon the pseudo labels produced by multiple unsupervised ranking models.
CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking
In this paper, we propose CODE, which first pre-trains an expert linking model by contrastive learning on AMiner such that it can capture the representation and matching patterns of experts without supervised signals, then it is fine-tuned between AMiner and external sources to enhance the models transferability in an adversarial manner.
Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation
Cold-start problem is a fundamental challenge for recommendation tasks.
Multi-task Additive Models for Robust Estimation and Automatic Structure Discovery
For high-dimensional observations in real environment, e. g., Coronal Mass Ejections (CMEs) data, the learning performance of previous methods may be degraded seriously due to the complex non-Gaussian noise and the insufficiency of prior knowledge on variable structure.
FLAME: Differentially Private Federated Learning in the Shuffle Model
In this work, by leveraging the \textit{privacy amplification} effect in the recently proposed shuffle model of differential privacy, we achieve the best of two worlds, i. e., accuracy in the curator model and strong privacy without relying on any trusted party.
FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection
To prevent privacy leakages from gradients that are calculated on users' sensitive data, local differential privacy (LDP) has been considered as a privacy guarantee in federated SGD recently.
GL2vec: Graph Embedding Enriched by Line Graphs with Edge Features
Specifically, it complements either the edge label information or the structural information which Graph2vec misses with the embeddings of the line graphs.
Robust Learning-based Predictive Control for Discrete-time Nonlinear Systems with Unknown Dynamics and State Constraints
Robust model predictive control (MPC) is a well-known control technique for model-based control with constraints and uncertainties.
Cascaded LSTMs based Deep Reinforcement Learning for Goal-driven Dialogue
Dialogue embeddings are learned by a LSTM at the middle of the network, and updated by the feeding of all turn embeddings.
Image Segmentation Based on Multiscale Fast Spectral Clustering
The computational complexity of Multiscale Fast Spectral Clustering is O(nlogn) and its memory cost is O(m).
PreCo: A Large-scale Dataset in Preschool Vocabulary for Coreference Resolution
We introduce PreCo, a large-scale English dataset for coreference resolution.
Semantic Aware Attention Based Deep Object Co-segmentation
Object co-segmentation is the task of segmenting the same objects from multiple images.
Regularized Modal Regression with Applications in Cognitive Impairment Prediction
Linear regression models have been successfully used to function estimation and model selection in high-dimensional data analysis.
Group Sparse Additive Machine
Among them, learning models with grouped variables have shown competitive performance for prediction and variable selection.
Modal Regression based Atomic Representation for Robust Face Recognition
In this paper, we propose a modal regression based atomic representation and classification (MRARC) framework to alleviate such limitation.
Error Analysis of Generalized Nyström Kernel Regression
Nystr\"{o}m method has been used successfully to improve the computational efficiency of kernel ridge regression (KRR).
