Search Results for author:
Found 202 papers, 81 papers with code
RBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax
To address this problem, this paper introduces a novel Radial Basis Function (RBF) distances to replace the commonly used inner products in the softmax loss function, such that it can adaptively assign losses to regularize the intra-class and inter-class distances by reshaping the relative differences, and thus creating more representative prototypes of classes to improve optimization.
软件标识符的自然语言规范性研究(Research on the Natural Language Normalness of Software Identifiers)
“软件源代码的理解则是软件协同开发与维护的核心, 而源代码中占半数以上的标识符的理解则在软件理解中起到重要作用, 传统软件工程主要研究通过命名规范限制标识符的命名过程以构造更易理解和交流的标识符。本文则在梳理分析常见编程语言命名规范的基础上, 提出一种全新的标识符可理解性评价标准。具体而言, 本文首先总结梳理了常见主流编程语言中的命名规范并类比自然语言语素概念本文提出基于软件语素的标识符构成过程, 即标识符的构成可被视为软件语素的生成、排列和连接过程。在此基础上, 本文提出一种结合自然语料库的软件标识符规范性评价方法, 用来衡量软件标识符是否易于理解。最后, 本文通过源代码理解数据集和乇乩乴乨乵乢平台中开源项目对规范性指标进行了验证性实验, 结果表明本文提出的规范性分数能够很好衡量软件项目的可理解性。”
TSVC:Tripartite Learning with Semantic Variation Consistency for Robust Image-Text Retrieval
In order to resolve this problem, we introduce a Tripartite learning with Semantic Variation Consistency (TSVC) for robust image-text retrieval.
ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding
ReARTeR addresses three core challenges: (1) misalignment between PRM and PEM, tackled through off-policy preference learning; (2) bias in PRM training data, mitigated by balanced annotation methods and stronger annotations for challenging examples; and (3) early-step bias in PRM, resolved through a temporal-difference-based look-ahead search strategy.
DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategy
Through comprehensive experiments on various facial image benchmarks and feature extractors, we demonstrate DynTracker's strength in breaking existing AFR methods and the superiority of DivTrackee in preventing user facial images from being identified by dynamic FR strategies.
HELPNet: Hierarchical Perturbations Consistency and Entropy-guided Ensemble for Scribble Supervised Medical Image Segmentation
Experimental results on three public datasets ACDC, MSCMRseg, and CHAOS show that HELPNet significantly outperforms state-of-the-art methods for scribble-based weakly supervised segmentation and achieves performance comparable to fully supervised methods.
Trigger$^3$: Refining Query Correction via Adaptive Model Selector
To tackle these, we propose Trigger$^3$, a large-small model collaboration framework that integrates the traditional correction model and LLM for query correction, capable of adaptively choosing the appropriate correction method based on the query and the correction results from the traditional correction model and LLM.
Nested Diffusion Models Using Hierarchical Latent Priors
Our approach employs a series of diffusion models to progressively generate latent variables at different semantic levels.
Can Targeted Clean-Label Poisoning Attacks Generalize?
In a common clean-label setting, they are achieved by slightly perturbing a subset of training samples given access to those specific targets.
PROFIT: A Specialized Optimizer for Deep Fine Tuning
Fine-tuning pre-trained models has become invaluable in computer vision and robotics.
LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks
Relying on promising watermark recovery accuracies, Deepfake detection is accomplished by assessing the consistency between the content-matched landmark perceptual watermark and the robustly recovered watermark of the suspect image.
PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement
Utilizing this progress prediction as a dense reward together with an adversarial push-back, we show that PROGRESSOR enables robots to learn complex behaviors without any external supervision.
GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
Large Language Models (LLMs) have shown impressive proficiency across a range of natural language processing tasks yet remain vulnerable to adversarial prompts, known as jailbreak attacks, carefully designed to elicit harmful responses from LLMs.
Length-Induced Embedding Collapse in Transformer-based Models
In this paper, we find that the performance degradation is due to a phenomenon called Length Collapse, where longer text embeddings collapse into a narrow space.
DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination
In the ever-evolving adversarial machine learning landscape, developing effective defenses against patch attacks has become a critical challenge, necessitating reliable solutions to safeguard real-world AI systems.
Predicting time-varying flux and balance in metabolic systems using structured neural-ODE processes
We develop a novel data-driven framework as an alternative to dynamic flux balance analysis, bypassing the demand for deep domain knowledge and manual efforts to formulate the optimization problem.
UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models
Our results show a significant alignment between benchmark scores and human preferences, with a Pearson correlation coefficient of 0. 78, confirming the effectiveness of the UCFE dataset and our evaluation approach.
ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
We discover hallucinations occur when the Knowledge FFNs in LLMs overemphasize parametric knowledge in the residual stream, while Copying Heads fail to effectively retain or integrate external knowledge from retrieved content.
LargePiG: Your Large Language Model is Secretly a Pointer Generator
To validate the effectiveness of LargePiG, we constructed two datasets for assessing the hallucination problems in query generation, covering both document and video scenarios.
Fast Second-Order Online Kernel Learning through Incremental Matrix Sketching and Decomposition
Moreover, the absence of incremental updates to manage approximate kernel space causes these algorithms to perform poorly in adversarial environments and real-world streaming recommendation datasets.
Generating Model Parameters for Controlling: Parameter Diffusion for Controllable Multi-Task Recommendation
To address this issue, we propose a novel controllable learning approach via Parameter Diffusion for controllable multi-task Recommendation (PaDiRec), which allows the customization and adaptation of recommendation model parameters to new task requirements without retraining.
Matrix Sketching in Bandits: Current Pitfalls and New Framework
To prevent this issue, we propose Dyadic Block Sketching, an innovative streaming matrix sketching approach that adaptively manages sketch size to constrain global spectral loss.
Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients
In this work, we study to release the potential of massive heterogeneous weak computing power to collaboratively train large-scale models on dispersed datasets.
Understanding Adversarially Robust Generalization via Weight-Curvature Index
Despite extensive research on adversarial examples, the underlying mechanisms of adversarially robust generalization, a critical yet challenging task for deep learning, remain largely unknown.
CreDes: Causal Reasoning Enhancement and Dual-End Searching for Solving Long-Range Reasoning Problems using LLMs
Large language models (LLMs) have demonstrated limitations in handling combinatorial optimization problems involving long-range reasoning, partially due to causal hallucinations and huge search space.
Enhancing elusive clues in knowledge learning by contrasting attention of language models
Causal language models acquire vast amount of knowledge from general text corpus during pretraining, but the efficiency of knowledge learning is known to be unsatisfactory, especially when learning from knowledge-dense and small-sized corpora.
Reliable and diverse evaluation of LLM medical knowledge mastery
Finally, these produced predicate variants are converted into textual language, resulting in a series of reliable and diverse test samples to evaluate whether LLMs fully master the given medical factual knowledge point.
Co-occurrence is not Factual Association in Language Models
Pretrained language models can encode a large amount of knowledge and utilize it for various reasoning tasks, yet they can still struggle to learn novel factual knowledge effectively from finetuning on limited textual demonstrations.
CSCE: Boosting LLM Reasoning by Simultaneous Enhancing of Casual Significance and Consistency
Chain-based reasoning methods like chain of thought (CoT) play a rising role in solving reasoning tasks for large language models (LLMs).
Enhancing Sequential Recommendations through Multi-Perspective Reflections and Iteration
Specifically, MoRE introduces three reflectors for generating LLM-based reflections on explicit preferences, implicit preferences, and collaborative signals.
Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications
We begin with FinLLaMA, pre-trained on a 52 billion token financial corpus, incorporating text, tables, and time-series data to embed comprehensive financial knowledge.
Stream-Based Ground Segmentation for Real-Time LiDAR Point Cloud Processing on FPGA
This paper presents a novel and fast approach for ground plane segmentation in a LiDAR point cloud, specifically optimized for processing speed and hardware efficiency on FPGA hardware platforms.
Accelerating Point Cloud Ground Segmentation: From Mechanical to Solid-State Lidars
In this study, we propose a novel parallel processing method for point cloud ground segmentation, aimed at the technology evolution from mechanical to solid-state Lidar (SSL).
Modeling Domain and Feedback Transitions for Cross-Domain Sequential Recommendation
In this paper, we propose $\text{Transition}^2$, a novel method to model transitions across both domains and types of user feedback.
InVi: Object Insertion In Videos Using Off-the-Shelf Diffusion Models
This process begins with inserting the object into a single frame using a ControlNet-based inpainting diffusion model, and then generating subsequent frames conditioned on features from an inpainted frame as an anchor to minimize the domain gap between the background and the object.
Preference-Guided Reinforcement Learning for Efficient Exploration
To tackle this issue, we introduce LOPE: Learning Online with trajectory Preference guidancE, an end-to-end preference-guided RL framework that enhances exploration efficiency in hard-exploration tasks.
A Survey of Controllable Learning: Methods and Applications in Information Retrieval
Controllability has become a crucial aspect of trustworthy machine learning, enabling learners to meet predefined targets and adapt dynamically at test time without requiring retraining as the targets shift.
Gaze-directed Vision GNN for Mitigating Shortcut Learning in Medical Image
In this paper, we propose a novel gaze-directed Vision GNN (called GD-ViG) to leverage the visual patterns of radiologists from gaze as expert knowledge, directing the network toward disease-relevant regions, and thereby mitigating shortcut learning.
Do Not Wait: Learning Re-Ranking Model Without User Feedback At Serving Time in E-Commerce
It means the modification is tailored to and only to the current request to capture the specific context of the request.
Two-Stage Depth Enhanced Learning with Obstacle Map For Object Navigation
The main bottlenecks of VON are strategies exploration and prior knowledge exploitation.
Do Parameters Reveal More than Loss for Membership Inference?
Membership inference attacks are used as a key tool for disclosure auditing.
Evolution-aware VAriance (EVA) Coreset Selection for Medical Image Classification
In the medical field, managing high-dimensional massive medical imaging data and performing reliable medical analysis from it is a critical challenge, especially in resource-limited environments such as remote medical facilities and mobile devices.
QAGCF: Graph Collaborative Filtering for Q&A Recommendation
Traditional recommendation methods treat the question-answer pair as a whole or only consider the answer as a single item, which overlooks the two challenges and cannot effectively model user interests.
Conditional Language Learning with Context
In this fashion, conditional finetuning achieves selective learning from a corpus, learning knowledge useful for downstream tasks while avoiding learning useless corpus statistics like topic biases.
Latent Intrinsics Emerge from Training to Relight
Image relighting is the task of showing what a scene from a source image would look like if illuminated differently.
ReCODE: Modeling Repeat Consumption with Neural ODE
In real-world recommender systems, such as in the music domain, repeat consumption is a common phenomenon where users frequently listen to a small set of preferred songs or artists repeatedly.
Leveraging Unknown Objects to Construct Labeled-Unlabeled Meta-Relationships for Zero-Shot Object Navigation
Furthermore, we propose the label-wise meta-correlation module (LWMCM) to harness relationships among objects with and without labels, and obtain enhanced objects information.
Effective In-Context Example Selection through Data Compression
In this paper, we propose a data compression approach to the selection of in-context examples.
Optimal Matrix Sketching over Sliding Windows
Matrix sketching, aimed at approximating a matrix $\boldsymbol{A} \in \mathbb{R}^{N\times d}$ consisting of vector streams of length $N$ with a smaller sketching matrix $\boldsymbol{B} \in \mathbb{R}^{\ell\times d}, \ell \ll N$, has garnered increasing attention in fields such as large-scale data analytics and machine learning.
Evaluation of Machine Translation Based on Semantic Dependencies and Keywords
To achieve a comprehensive and in-depth evaluation of the semantic correctness of sentences, the experimental results show that the accuracy of the evaluation algorithm has been improved compared with similar methods, and it can more accurately measure the semantic correctness of machine translation.
Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations
We introduce a neural "taxonomical" semantic parser to utilize this new representation system of predicates, and compare it with a standard neural semantic parser trained on the traditional meaning representation format, employing a novel challenge set and evaluation metric for evaluation.
Residual Connections Harm Generative Representation Learning
We show that introducing a weighting factor to reduce the influence of identity shortcuts in residual networks significantly enhances semantic feature learning in generative representation learning frameworks, such as masked autoencoders (MAEs) and diffusion models.
UniSAR: Modeling User Transition Behaviors between Search and Recommendation
In this paper, we propose a framework named UniSAR that effectively models the different types of fine-grained behavior transitions for providing users a Unified Search And Recommendation service.
PMB5: Gaining More Insight into Neural Semantic Parsing with Challenging Benchmarks
The Parallel Meaning Bank (PMB) serves as a corpus for semantic processing with a focus on semantic parsing and text generation.
To Search or to Recommend: Predicting Open-App Motivation with Neural Hawkes Process
The model, referred to as Neural Hawkes Process-based Open-App Motivation prediction model (NHP-OAM), employs a hierarchical transformer and a novel intensity function to encode multiple factors, and open-app motivation prediction layer to integrate time and user-specific information for predicting users' open-app motivations.
Large Language Models Enhanced Collaborative Filtering
In this paper, drawing inspiration from the in-context learning and chain of thought reasoning in LLMs, we propose the Large Language Models enhanced Collaborative Filtering (LLM-CF) framework, which distils the world knowledge and reasoning capabilities of LLMs into collaborative filtering.
IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution History
This poses a new challenge for existing imitation learning approaches that can only utilize data from experienced experts.
An Item is Worth a Prompt: Versatile Image Editing with Disentangled Control
Building on the success of text-to-image diffusion models (DPMs), image editing is an important application to enable human interaction with AI-generated content.
A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applications
However, since FL enables a continuous share of knowledge among participants with each communication round while not allowing local data to be accessed by other participants, FTL faces many unique challenges that are not present in TL.
AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
In this paper, we propose AutoDefense, a multi-agent defense framework that filters harmful responses from LLMs.
On the Decision-Making Abilities in Role-Playing using Large Language Models
Large language models (LLMs) are now increasingly utilized for role-playing tasks, especially in impersonating domain-specific experts, primarily through role-playing prompts.
RFI-DRUnet: Restoring dynamic spectra corrupted by radio frequency interference -- Application to pulsar observations
Conversely, this work proposes to tackle RFI mitigation as a joint detection and restoration that allows parts of the dynamic spectrum affected by RFI to be not only identified but also recovered.
FinBen: A Holistic Financial Benchmark for Large Language Models
Our evaluation of 15 representative LLMs, including GPT-4, ChatGPT, and the latest Gemini, reveals several key findings: While LLMs excel in IE and textual analysis, they struggle with advanced reasoning and complex tasks like text generation and forecasting.
FairSync: Ensuring Amortized Group Exposure in Distributed Recommendation Retrieval
Specifically, FairSync resolves the issue by moving it to the dual space, where a central node aggregates historical fairness data into a vector and distributes it to all servers.
Dólares or Dollars? Unraveling the Bilingual Prowess of Financial LLMs Between Spanish and English
We evaluate our model and existing LLMs using FLARE-ES, the first comprehensive bilingual evaluation benchmark with 21 datasets covering 9 tasks.
Learning Diverse Policies with Soft Self-Generated Guidance
However, existing methods often require these experiences to be successful and may overly exploit them, which can cause the agent to adopt suboptimal behaviors.
Curator: Efficient Indexing for Multi-Tenant Vector Databases
Vector databases have emerged as key enablers for bridging intelligent applications with unstructured data, providing generic search and management support for embedding vectors extracted from the raw unstructured data.
Leveraging Frequency Domain Learning in 3D Vessel Segmentation
In this study, we leverage Fourier domain learning as a substitute for multi-scale convolutional kernels in 3D hierarchical segmentation models, which can reduce computational expenses while preserving global receptive fields within the network.
O-PRESS: Boosting OCT axial resolution with Prior guidance, Recurrence, and Equivariant Self-Supervision
Optical coherence tomography (OCT) is a noninvasive technology that enables real-time imaging of tissue microanatomies.
Trajectory-Oriented Policy Optimization with Sparse Rewards
The proposed algorithm undergoes evaluation across extensive discrete and continuous control tasks with sparse and misleading rewards.
Policy Optimization with Smooth Guidance Learned from State-Only Demonstrations
The sparsity of reward feedback remains a challenging problem in online deep reinforcement learning (DRL).
Adaptive trajectory-constrained exploration strategy for deep reinforcement learning
Deep reinforcement learning (DRL) faces significant challenges in addressing the hard-exploration problems in tasks with sparse or deceptive rewards and large state spaces.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
+1
Deciphering 'What' and 'Where' Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations
We present an approach for analyzing grouping information contained within a neural network's activations, permitting extraction of spatial layout and semantic segmentation from the behavior of large pre-trained vision models.
Neural Retrievers are Biased Towards LLM-Generated Content
Surprisingly, our findings indicate that neural retrieval models tend to rank LLM-generated documents higher.
Integrating View Conditions for Image Synthesis
In the field of image processing, applying intricate semantic modifications within existing images remains an enduring challenge.
Multi-View Variational Autoencoder for Missing Value Imputation in Untargeted Metabolomics
By learning the latent representations of both omics data, our method can effectively impute missing metabolomics values based on genomic information.
Provably Robust Cost-Sensitive Learning via Randomized Smoothing
Built upon the notion of cost-sensitive certified radius, we first illustrate how to adapt the standard certification algorithm of randomized smoothing to produce tight robustness certificates for any binary cost matrix, and then develop a robust training method to promote certified cost-sensitive robustness while maintaining the model's overall accuracy.
Transferable Availability Poisoning Attacks
We consider availability data poisoning attacks, where an adversary aims to degrade the overall test accuracy of a machine learning model by crafting small perturbations to its training data.
Generating Less Certain Adversarial Examples Improves Robust Generalization
Therefore, we hypothesize that generating less certain adversarial examples improves robust generalization, and propose a formal definition of adversarial certainty that captures the variance of the model's predicted logits on adversarial examples.
Structural Adversarial Objectives for Self-Supervised Representation Learning
Within the framework of generative adversarial networks (GANs), we propose objectives that task the discriminator for self-supervised representation learning via additional structural modeling responsibilities.
PINF: Continuous Normalizing Flows for Physics-Constrained Deep Learning
The normalization constraint on probability density poses a significant challenge for solving the Fokker-Planck equation.
Generative Retrieval with Semantic Tree-Structured Item Identifiers via Contrastive Learning
To obtain efficiency and effectiveness, this paper introduces a generative retrieval framework, namely SEATER, which learns SEmAntic Tree-structured item identifiERs via contrastive learning.
HyperBandit: Contextual Bandit with Hypernewtork for Time-Varying User Preferences in Streaming Recommendation
In real-world streaming recommender systems, user preferences often dynamically change over time (e. g., a user may have different preferences during weekdays and weekends).
LTP-MMF: Towards Long-term Provider Max-min Fairness Under Recommendation Feedback Loops
Multi-stakeholder recommender systems involve various roles, such as users, and providers.
SciMRC: Multi-perspective Scientific Machine Reading Comprehension
However, the dataset has ignored the fact that different readers may have different levels of understanding of the text, and only includes single-perspective question-answer pairs, leading to a lack of consideration of different perspectives.
Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery
In this paper, we propose a method to construct a boundary that discriminates safe and unsafe states.
Discourse Representation Structure Parsing for Chinese
Previous work has predominantly focused on monolingual English semantic parsing.
KuaiSAR: A Unified Search And Recommendation Dataset
We believe this dataset will serve as a catalyst for innovative research and bridge the gap between academia and industry in understanding the S&R services in practical, real-world applications.
Controllable Multi-Objective Re-ranking with Policy Hypernetworks
In this paper, we propose a framework called controllable multi-objective re-ranking (CMR) which incorporates a hypernetwork to generate parameters for a re-ranking model according to different preference weights.
PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance
This paper introduces PIXIU, a comprehensive framework including the first financial LLM based on fine-tuning LLaMA with instruction data, the first instruction data with 136K data samples to support the fine-tuning, and an evaluation benchmark with 5 tasks and 9 datasets.
When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation
In our paper, we propose a Search-Enhanced framework for the Sequential Recommendation (SESRec) that leverages users' search interests for recommendation, by disentangling similar and dissimilar representations within S&R behaviors.
Robust Image Ordinal Regression with Controllable Image Generation
Image ordinal regression has been mainly studied along the line of exploiting the order of categories.
Uncovering ChatGPT's Capabilities in Recommender Systems
The debut of ChatGPT has recently attracted the attention of the natural language processing (NLP) community and beyond.
A Lightweight Recurrent Learning Network for Sustainable Compressed Sensing
While the initial reconstruction sub-network has a hierarchical structure to progressively recover the image, reducing the number of parameters, the residual reconstruction sub-network facilitates recurrent residual feature extraction via recurrent learning to perform both feature fusion and deep reconstructions across different scales.
Transition System Representation of Boolean Control Networks
The first kind of representation is state-based, which converts a BCN into a TS with either distinct control or non-distinct control.
CLCLSA: Cross-omics Linked embedding with Contrastive Learning and Self Attention for multi-omics integration with incomplete multi-omics data
Integration of heterogeneous and high-dimensional multi-omics data is becoming increasingly important in understanding genetic data.
Aggregated (Bi-)Simulation of Finite Valued Networks
Then the overall network can be approximated by the quotient systems of each blocks, which is called the aggregated simulation.
Reproduction number of SARS-CoV-2 Omicron variants, China, December 2022-January 2023
China adjusted the zero-COVID strategy in late 2022, triggering an unprecedented Omicron wave.
P-MMF: Provider Max-min Fairness Re-ranking in Recommender System
In this paper, we proposed an online re-ranking model named Provider Max-min Fairness Re-ranking (P-MMF) to tackle the problem.
Semi-Tensor Product of Hypermatrices with Application to Compound Hypermatrices
Some basic properties of the STP of matrices are extended to the STP of hypermatrices.
Bridging The Gap: Entailment Fused-T5 for Open-retrieval Conversational Machine Reading Comprehension
Open-retrieval conversational machine reading comprehension (OCMRC) simulates real-life conversational interaction scenes.
Analysis of Discrete-Time Switched Linear Systems under Logic Dynamic Switchings
The control properties of discrete-time switched linear systems (SLS) with switching signals generated by logical dynamic systems are studied using the semi-tensor product (STP) approach.
PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds
To alleviate the cost of hyperparameter tuning and iterative pseudo labeling, we develop a population-based data augmentation framework for 3D detection, named AutoPseudoAugment.
Law Article-Enhanced Legal Case Matching: a Causal Learning Approach
We show that the framework is model-agnostic, and a number of legal case matching models can be applied as the underlying models.
ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension
Conversational machine reading comprehension (CMRC) aims to assist computers to understand an natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text.
MICO: Selective Search with Mutual Information Co-training
In contrast to traditional exhaustive search, selective search first clusters documents into several groups before all the documents are searched exhaustively by a query, to limit the search executed within one group or only a few groups.
Invariant and Dual Invariant Subspaces of $k$-valued Networks
Finally, the relationship between state invariant subspace and dual invariant subspace of a network is investigated.
Adversarial Attacks on ASR Systems: An Overview
With the development of hardware and algorithms, ASR(Automatic Speech Recognition) systems evolve a lot.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Handling Data Heterogeneity in Federated Learning via Knowledge Distillation and Fusion
The key idea in FedKF is to let the server return the global knowledge to be fused with the local knowledge in each training round so that the local model can be regularized towards the global optima.
Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices
Our goal is to train a large neural network language model (NNLM) on compute-constrained devices while preserving privacy using FL and DP.
Feature Forgetting in Continual Representation Learning
To study the feature forgetting problem, we create a synthetic dataset to identify and visualize the prevalence of feature forgetting in neural networks.
Cross-Lingual Phrase Retrieval
In this paper, we propose XPR, a cross-lingual phrase retriever that extracts phrase representations from unlabeled example sentences.
Reinforcement Re-ranking with 2D Grid-based Recommendation Panels
Then, it defines \emph{the MDP discrete time steps as the ranks in the initial ranking list, and the actions as the prediction of the user-item preference and the selection of the slots}.
Unbiased Top-k Learning to Rank with Causal Likelihood Decomposition
An extension to the pairwise neural ranking is also developed.
A Model-Agnostic Causal Learning Framework for Recommendation using Search Data
In this paper, we propose a model-agnostic framework named IV4Rec that can effectively decompose the embedding vectors into these two parts, hence enhancing recommendation results.
Combining Reinforcement Learning and Inverse Reinforcement Learning for Asset Allocation Recommendations
We suggest a simple practical method to combine the human and artificial intelligence to both learn best investment practices of fund managers, and provide recommendations to improve them.
Hidden Order of Boolean Networks
It is a common belief that the order of a Boolean network is mainly determined by its attractors, including fixed points and cycles.
A Divide-and-Merge Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentation
The proposed algorithm is implemented with C++ and wrapped as a python function.
A Technical Survey and Evaluation of Traditional Point Cloud Clustering Methods for LiDAR Panoptic Segmentation
To our best knowledge, we are the first to attempt the point cloud panoptic segmentation with clustering algorithms.
Understanding Intrinsic Robustness Using Label Uncertainty
A fundamental question in adversarial machine learning is whether a robust classifier exists for a given task.
RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
These larger detection ranges require more efficient and accurate detection models.
To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels
3D object detection is vital for many robotics applications.
Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Incorporating with a set of randomized strategies for well-designed data transformations over the training set, ContRE adopts classification errors and Fisher ratios on the generated contrastive examples to assess and analyze the generalization performance of deep models in complement with a testing set.
Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
Unsupervised object re-identification targets at learning discriminative representations for object retrieval without any annotations.
Optimization Variance: Exploring Generalization Properties of DNNs
Unlike the conventional wisdom in statistical learning theory, the test error of a deep neural network (DNN) often demonstrates double descent: as the model complexity increases, it first follows a classical U-shaped curve and then shows a second descent.
Multi-Grained Knowledge Distillation for Named Entity Recognition
To maximally assimilate knowledge into the student model, we propose a multi-grained distillation scheme, which integrates cross entropy involved in conditional random field (CRF) and fuzzy learning. To validate the effectiveness of our proposal, we conducted a comprehensive evaluation on five NER benchmarks, reporting cross-the-board performance gains relative to competing prior-arts.
DCAP: Deep Cross Attentional Product Network for User Response Prediction
Prior studies in predicting user response leveraged the feature interactions by enhancing feature vectors with products of features to model second-order or high-order cross features, either explicitly or implicitly.
ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework for Human Activity Recognition
On the one hand, multiple views across tasks possibly relate to each other under practical situations.