Search Results for author:
Found 123 papers, 62 papers with code
Utilizing Multimodal Feature Consistency to Detect Adversarial Examples on Clinical Summaries
Among the modalities of medical data, the clinical summaries have higher risks to be attacked because they are generated by third-party companies.
Enchancing the Collaborative Interlingual Index for Digital Humanities: Cross-linguistic Analysis in the Domain of Theology
To do this, we propose to build a cross-lingual wordnet within the do-main of theology.
Reinforced Latent Reasoning for LLM-based Recommendation
However, these methods face significant practical limitations due to (1) the difficulty of obtaining high-quality CoT data in recommendation and (2) the high inference latency caused by generating CoT reasoning.
LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning
LoTA-QAF operates through a combination of: i) A custom-designed ternary adaptation (TA) that aligns ternary weights with the quantization grid and uses these ternary weights to adjust quantized weights.
$\text{R}^2\text{ec}$: Towards Large Recommender Models with Reasoning
To address these issues, we propose \name, a unified large recommender model with intrinsic reasoning capabilities.
MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation
To fill these gaps, we present MTR-Bench for LLMs' Multi-Turn Reasoning evaluation.
NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search
Generative AI search is reshaping information retrieval by offering end-to-end answers to complex queries, reducing users' reliance on manually browsing and summarizing multiple web pages.
DRC: Enhancing Personalized Image Generation via Disentangled Representation Composition
Extensive experiments on two benchmarks demonstrate that DRC shows competitive performance while effectively mitigating the guidance collapse issue, underscoring the importance of disentangled representation learning for controllable and effective personalized image generation.
Understanding Accuracy-Fairness Trade-offs in Re-ranking through Elasticity in Economics
Prior work has identified a trade-off between ranking accuracy and item fairness.
Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Models
Psychological evidence highlights the influence of personality traits on user interaction behaviors.
Unifying Search and Recommendation: A Generative Paradigm Inspired by Information Theory
Previous approaches mainly follow a discriminative paradigm, utilizing shared encoders to process input features and task-specific heads to perform each task.
Inference on effect size after multiple hypothesis testing
We propose new estimators and confidence intervals that provide valid inferences on the effect sizes of the significant effects after multiple hypothesis testing.
Exploring Training and Inference Scaling Laws in Generative Retrieval
Generative retrieval has emerged as a novel paradigm that leverages large language models (LLMs) to autoregressively generate document identifiers.
OmniGeo: Towards a Multimodal Large Language Models for Geospatial Artificial Intelligence
In this paper, we explore the potential of multimodal LLMs (MLLM) for geospatial artificial intelligence (GeoAI), a field that leverages spatial data to address challenges in domains including Geospatial Semantics, Health Geography, Urban Geography, Urban Perception, and Remote Sensing.
FinTMMBench: Benchmarking Temporal-Aware Multi-Modal RAG in Finance
Finance decision-making often relies on in-depth data analysis across various data sources, including financial tables, news articles, stock prices, etc.
Personalized Text Generation with Contrastive Activation Steering
Personalized text generation aims to infer users' writing style preferences from their historical texts and generate outputs that faithfully reflect these stylistic characteristics.
Personalized Generation In Large Model Era: A Survey
In the era of large models, content generation is gradually shifting to Personalized Generation (PGen), tailoring content to individual preferences and needs.
Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization
Personalizing Large Language Models (LLMs) has become a critical step in facilitating their widespread application to enhance individual life experiences.
LLM Knows Geometry Better than Algebra: Numerical Understanding of LLM-Based Agents in A Trading Arena
Recent advancements in large language models (LLMs) have significantly improved performance in natural language processing tasks.
Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment
To efficiently obtain and utilize such responses, we propose a self-improving DPO framework that enables LLMs to self-generate and select Pareto-optimal responses for self-supervised preference alignment.
DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing
Large Language Models (LLMs) are widely applied in decision making, but their deployment is threatened by jailbreak attacks, where adversarial users manipulate model behavior to bypass safety measures.
DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Demonstration and Reasoning
Large Language Models (LLMs) exhibit strong natural language processing capabilities but also inherit and amplify societal biases, including gender bias, raising fairness concerns.
TokenSkip: Controllable Chain-of-Thought Compression in LLMs
Chain-of-Thought (CoT) has been proven effective in enhancing the reasoning capabilities of large language models (LLMs).
HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning
To investigate this question, we present the first extensive robustness evaluation of LLMs in commonsense reasoning.
Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models
Pre-training large language models (LLMs) on vast text corpora enhances natural language processing capabilities but risks encoding social biases, particularly gender bias.
Order-agnostic Identifier for Large Language Model-based Generative Recommendation
To address these issues, we propose two fundamental principles for item identifier design: 1) integrating both CF and semantic information to fully capture multi-dimensional item information, and 2) designing order-agnostic identifiers without token dependency, mitigating the local optima issue and achieving simultaneous generation for generation efficiency.
Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
To overcome these limitations, we first theoretically demonstrate that the MMF-constrained objective can be essentially reformulated as a group-weighted optimization objective.
Holistically Guided Monte Carlo Tree Search for Intricate Information Seeking
We reformulate the task as a progressive information collection process with a knowledge memory and unite an adaptive checklist with multi-perspective reward modeling in MCTS.
Large Language Models for Recommendation with Deliberative User Preference Alignment
We then introduce the Deliberative User Preference Alignment framework, designed to enhance reasoning capabilities by utilizing verbalized user feedback in a step-wise manner to tackle this task.
Dynamic Multimodal Fusion via Meta-Learning Towards Micro-Video Recommendation
In this paper, we develop a novel meta-learning-based multimodal fusion framework called Meta Multimodal Fusion (MetaMMF), which dynamically assigns parameters to the multimodal fusion function for each micro-video during its representation learning.
Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation
During training, LLM generates candidate lists to enhance the ranking ability of SRM in collaborative scenarios and enables SRM to update adaptively to capture real-time user interests.
Optimize Incompatible Parameters through Compatibility-aware Knowledge Integration
The integrated model can be used directly for inference or for further fine-tuning.
PINN-EMFNet: PINN-based and Enhanced Multi-Scale Feature Fusion Network for Breast Ultrasound Images Segmentation
With the rapid development of deep learning and computer vision technologies, medical image segmentation plays a crucial role in the early diagnosis of breast cancer.
Length Controlled Generation for Black-box LLMs
Large language models (LLMs) have demonstrated impressive instruction following capabilities, while still struggling to accurately manage the length of the generated text, which is a fundamental requirement in many real-world applications.
SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation
To adapt SILMM to LMMs with continuous features, we propose a diversity mechanism to obtain diverse representations and a kernel-based continuous DPO for alignment.
A Dimension-Agnostic Bootstrap Anderson-Rubin Test For Instrumental Variable Regressions
By deriving strong approximations for the test statistic and its bootstrap counterpart, we show that our new test has a correct asymptotic size regardless of whether the number of IVs is fixed or increasing -- allowing, but not requiring, the number of IVs to exceed the sample size.
STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training
Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but struggle with compositional reasoning that requires multi-step spatio-temporal inference across object relations, interactions, and events.
Self-Calibrated Listwise Reranking with Large Language Models
Large language models (LLMs), with advanced linguistic capabilities, have been employed in reranking tasks through a sequence-to-sequence approach.
Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning
This work explores adapting to dynamic user interests without any model updates by leveraging In-Context Learning (ICL), which allows LLMs to learn new tasks from few-shot examples provided in the input.
Causality-Enhanced Behavior Sequence Modeling in LLMs for Personalized Recommendation
Recent advancements in recommender systems have focused on leveraging Large Language Models (LLMs) to improve user preference modeling, yielding promising outcomes.
MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding
Large Vision-Language Models (LVLMs) have achieved remarkable performance in many vision-language tasks, yet their capabilities in fine-grained visual understanding remain insufficiently evaluated.
Large Language Models Empowered Personalized Web Agents
To overcome the limitation, we first formulate the task of LLM-empowered personalized Web agents, which integrate personalized data and user instructions to personalize instruction comprehension and action execution.
Personalized Image Generation with Large Multimodal Models
Personalized content filtering, such as recommender systems, has become a critical infrastructure to alleviate information overload.
FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection
Federated learning (FL) is a promising machine learning paradigm that collaborates with client models to capture global knowledge.
Efficient Inference for Large Language Model-based Generative Recommendation
To alleviate this, we consider 1) boosting top-K sequence alignment between the draft model and the target LLM, and 2) relaxing the verification strategy to reduce trivial LLM calls.
Proactive Recommendation in Social Networks: Steering User Interest via Neighbor Influence
To answer this question, we resort to causal inference and formalize PRSN as: (1) estimating the potential feedback of a user on an item, under the network interference by the item's exposure to the user's neighbors; and (2) adjusting the exposure of a target item to target users' neighbors to trade off steering performance and the damage to the neighbors' experience.
Leveraging LLMs for Influence Path Planning in Proactive Recommendation
To broaden user horizons, proactive recommender systems aim to guide user interest to gradually like a target item beyond historical interests through an influence path, i. e., a sequence of recommended items.
Debias Can be Unreliable: Mitigating Bias Issue in Evaluating Debiasing Recommendation
Recent work has improved recommendation models remarkably by equipping them with debiasing methods.
Gradient Wild Bootstrap for Instrumental Variable Quantile Regressions with Weak and Few Clusters
For the Wald inference, we show that our wild bootstrap Wald test, with or without studentization using the cluster-robust covariance estimator (CRVE), controls size asymptotically up to a small error as long as the parameter of endogenous variable is strongly identified in at least one of the clusters.
Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models
Multimodal information is a double-edged sword.
Revolutionizing Text-to-Image Retrieval as Autoregressive Token-to-Voken Generation
Despite its great potential, existing generative approaches are limited due to the following issues: insufficient visual information in identifiers, misalignment with high-level semantics, and learning gap towards the retrieval target.
Optimal Kernel Choice for Score Function-based Causal Discovery
In this paper, we propose a kernel selection method within the generalized score function that automatically selects the optimal kernel that best fits the data.
Debiased Recommendation with Noisy Feedback
Ratings of a user to most items in recommender systems are usually missing not at random (MNAR), largely because users are free to choose which items to rate.
CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG
To address this issue, we explore the task of "credibility-aware RAG", in which LLMs automatically adjust the influence of retrieved documents based on their credibility scores to counteract misinformation.
Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs
CFMAD presets the stances of LLMs to override their inherent biases by compelling LLMs to generate justifications for a predetermined answer's correctness.
BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detection
Vision-based roadside 3D object detection has attracted rising attention in autonomous driving domain, since it encompasses inherent advantages in reducing blind spots and expanding perception range.
TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models
How humans can effectively and efficiently acquire images has always been a perennial question.
Text-like Encoding of Collaborative Information in Large Language Models for Recommendation
BinLLM converts collaborative embeddings from external models into binary sequences -- a specific text format that LLMs can understand and operate on directly, facilitating the direct usage of collaborative information in text-like format by LLMs.
Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction
From the examiner perspective, we define four evaluation tasks for error identification and correction along with a new dataset with annotated error types and steps.
Treatment Effect Estimation for User Interest Exploration on Recommender Systems
The empirical results validate the effectiveness of UpliftRec in discovering users' hidden interests while achieving superior recommendation accuracy.
Learnable Item Tokenization for Generative Recommendation
Utilizing powerful Large Language Models (LLMs) for generative recommendation has attracted much attention.
Don't Say No: Jailbreaking LLM by Suppressing Refusal
Ensuring the safety alignment of Large Language Models (LLMs) is crucial to generating responses consistent with human values.
A Survey of Generative Search and Recommendation in the Era of Large Language Models
With the information explosion on the Web, search and recommendation are foundational infrastructures to satisfying users' information needs.
Exact and Efficient Unlearning for Large Language Model-based Recommendation
The evolving paradigm of Large Language Model-based Recom- mendation (LLMRec) customizes Large Language Models (LLMs) through parameter-efficient fine-tuning (PEFT) using recommenda- tion data.
Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing
Randomized smoothing is the primary certified robustness method for accessing the robustness of deep learning models to adversarial perturbations in the l2-norm, by adding isotropic Gaussian noise to the input image and returning the majority votes over the base classifier.
Decentralizing Coherent Joint Transmission Precoding via Fast ADMM with Deterministic Equivalents
Simulation results demonstrate the effectiveness of our proposed decentralized precoding scheme, which achieves performance similar to the optimal centralized precoding scheme.
$\textit{LinkPrompt}$: Natural and Universal Adversarial Attacks on Prompt-based Language Models
Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks across various natural language processing (NLP) tasks.
Decentralizing Coherent Joint Transmission Precoding via Deterministic Equivalents
In order to control the inter-cell interference for a multi-cell multi-user multiple-input multiple-output network, we consider the precoder design for coordinated multi-point with downlink coherent joint transmission.
Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection
Self-detection for Large Language Models (LLMs) seeks to evaluate the trustworthiness of the LLM's output by leveraging its own capabilities, thereby alleviating the issue of output hallucination.
Proactive Recommendation with Iterative Preference Guidance
However, such recommender systems passively cater to user interests and even reinforce existing interests in the feedback loop, leading to problems like filter bubbles and opinion polarization.
DESERE: The 1st Workshop on Decentralised Search and Recommendation
The DESERE Workshop, our First Workshop on Decentralised Search and Recommendation, offers a platform for researchers to explore and share innovative ideas on decentralised web services, mainly focusing on three major topics: (i) societal impact of decentralised systems: their effect on privacy, policy, and regulation; (ii) decentralising applications: algorithmic and performance challenges that arise from decentralisation; and (iii) infrastructure to support decentralised systems and services: peer-to-peer networks, routing, and performance evaluation tools
The 2nd Workshop on Recommendation with Generative Models
The rise of generative models has driven significant advancements in recommender systems, leaving unique opportunities for enhancing users' personalized recommendations.
Discriminative Probing and Tuning for Text-to-Image Generation
We present a discriminative adapter built on T2I models to probe their discriminative abilities on two representative tasks and leverage discriminative fine-tuning to improve their text-image alignment.
Maximizing Energy Charging for UAV-assisted MEC Systems with SWIPT
By leveraging the SWIPT technique, the UAV can simultaneously transmit energy and the computing results during the downlink period.
Uplift Modeling for Target User Attacks on Recommender Systems
UBA estimates the treatment effect on each target user and optimizes the allocation of fake user budgets to maximize the attack performance.
Lower-Left Partial AUC: An Effective and Efficient Optimization Metric for Recommendation
Compared to AUC, LLPAUC considers only the partial area under the ROC curve in the Lower-Left corner to push the optimization focus on Top-K. We provide theoretical validation of the correlation between LLPAUC and Top-K ranking metrics and demonstrate its robustness to noisy user feedback.
Prospect Personalized Recommendation on Large Language Model-based Agent Platform
Additionally, we prospect the evolution of Rec4Agentverse and conceptualize it into three stages based on the enhancement of the interaction and information exchange among Agent Items, Agent Recommender, and the user.
Diffusion Models for Generative Outfit Recommendation
Outfit Recommendation (OR) in the fashion domain has evolved through two stages: Pre-defined Outfit Recommendation and Personalized Outfit Composition.
Item-side Fairness of Large Language Model-based Recommendation System
Towards this goal, we develop a concise and effective framework called IFairLRS to enhance the item-side fairness of an LRS.
Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond
Building upon this capability, we propose to enable multimodal large language models (MLLMs) to memorize and recall images within their parameters.
Distillation Enhanced Generative Retrieval
Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target.
A Federated Framework for LLM-based Recommendation
However, directly applying Fed4Rec in the LLM context introduces two challenges: 1) exacerbated client performance imbalance, which ultimately impacts the system's long-term effectiveness, and 2) substantial client resource costs, posing a high demand for clients' both computational and storage capability to locally train and infer LLMs.
Understanding and Counteracting Feature-Level Bias in Click-Through Rate Prediction
We conduct a theoretical analysis of the learning process for the weights in the linear component, revealing how group-wise properties of training data influence them.
Data-efficient Fine-tuning for LLM-based Recommendation
To pursue the two objectives, we propose a novel data pruning method based on two scores, i. e., influence score and effort score, to efficiently identify the influential samples.
GOODAT: Towards Test-time Graph Out-of-Distribution Detection
To identify and reject OOD samples with GNNs, recent studies have explored graph OOD detection, often focusing on training a specific model or modifying the data on top of a well-trained GNN.
Temporally and Distributionally Robust Optimization for Cold-Start Recommendation
They learn a feature extractor on warm-start items to align feature representations with interactions, and then leverage the feature extractor to extract the feature representations of cold-start items for interaction prediction.
A Study of Implicit Ranking Unfairness in Large Language Models
Worse still, in this paper, we identify a subtler form of discrimination in LLMs, termed \textit{implicit ranking unfairness}, where LLMs exhibit discriminatory ranking patterns based solely on non-sensitive user profiles, such as user names.
Attack Prompt Generation for Red Teaming and Defending Large Language Models
Furthermore, we propose a defense framework that fine-tunes victim LLMs through iterative interactions with the attack framework to enhance their safety against red teaming attacks.
Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation
Harnessing Large Language Models (LLMs) for recommendation is rapidly emerging, which relies on two fundamental steps to bridge the recommendation item space and the language space: 1) item indexing utilizes identifiers to represent items in the language space, and 2) generation grounding associates LLMs' generated token sequences to in-corpus items.
RecAD: Towards A Unified Library for Recommender Attack and Defense
Despite significant research progress in recommender attack and defense, there is a lack of a widely-recognized benchmarking standard in the field, leading to unfair performance comparison and limited credibility of experiments.
I3: Intent-Introspective Retrieval Conditioned on Instructions
Recent studies indicate that dense retrieval models struggle to perform well on a wide variety of retrieval tasks that lack dedicated training data, as different retrieval tasks often entail distinct search intents.
A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems
As the focus on Large Language Models (LLMs) in the field of recommendation intensifies, the optimization of LLMs for recommendation purposes (referred to as LLM4Rec) assumes a crucial role in augmenting their effectiveness in providing recommendations.
General Debiasing for Multimodal Sentiment Analysis
To this end, we propose a general debiasing framework based on Inverse Probability Weighting (IPW), which adaptively assigns small weights to the samples with larger bias (i. e., the severer spurious correlations).
Robust Prompt Optimization for Large Language Models Against Distribution Shifts
In this light, we propose a new problem of robust prompt optimization for LLMs against distribution shifts, which requires the prompt optimized over the labeled source group can simultaneously generalize to an unlabeled target group.
Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation
The remarkable achievements of Large Language Models (LLMs) have led to the emergence of a novel recommendation paradigm -- Recommendation via LLM (RecLLM).
TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation
We have demonstrated that the proposed TALLRec framework can significantly enhance the recommendation capabilities of LLMs in the movie and book domains, even with a limited dataset of fewer than 100 samples.
Reformulating CTR Prediction: Learning Invariant Feature Interactions for Recommendation
However, such a manner inevitably learns unstable feature interactions, i. e., the ones that exhibit strong correlations in historical data but generalize poorly for future serving.
Learnable Pillar-based Re-ranking for Image-Text Retrieval
Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities.
Diffusion Recommender Model
In light of the impressive advantages of Diffusion Models (DMs) over traditional generative models in image synthesis, we propose a novel Diffusion Recommender Model (named DiffRec) to learn the generative process in a denoising manner.
Generative Recommendation: Towards Next-generation Recommender Paradigm
However, such a retrieval-based recommender paradigm faces two limitations: 1) the human-generated items in the corpus might fail to satisfy the users' diverse information needs, and 2) users usually adjust the recommendations via inefficient passive feedback, e. g., clicks.
Causal Disentangled Recommendation Against User Preference Shifts
Inspired by the causal graph, our key considerations to handle preference shifts lie in modeling the interaction generation procedure by: 1) capturing the preference shifts across environments for accurate preference prediction, and 2) disentangling the sparse influence from user preference to interactions for accurate effect estimation of preference.
Wasserstein Adversarial Examples on Univariant Time Series Data
In this work, we propose adversarial examples in the Wasserstein space for time series data for the first time and utilize Wasserstein distance to bound the perturbation between normal examples and adversarial examples.
AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network
Moreover, to improve the performance of the downstream graph learning task, attribute completion and the training of the heterogeneous GNN should be jointly optimized rather than viewed as two separate processes.
Mitigating Spurious Correlations for Self-supervised Recommendation
This objective requires to 1) automatically mask spurious features without supervision, and 2) block the negative effect transmission from spurious features to other features during SSL.
Causal Intervention for Fairness in Multi-behavior Recommendation
Specifically, we find that: 1) item popularity is a confounder between the exposed items and users' post-click interactions, leading to the first unfairness; and 2) some hidden confounders (e. g., the reputation of item producers) affect both item popularity and quality, resulting in the second unfairness.
Causal Inference in Recommender Systems: A Survey and Future Directions
Existing recommender systems extract user preferences based on the correlation in data, such as behavioral correlation in collaborative filtering, feature-feature, or feature-behavior correlation in click-through rate prediction.
Counterfactual Reasoning for Out-of-distribution Multimodal Sentiment Analysis
Inspired by this, we devise a model-agnostic counterfactual framework for multimodal sentiment analysis, which captures the direct effect of textual modality via an extra text model and estimates the indirect one by a multimodal model.
A Conditional Linear Combination Test with Many Weak Instruments
Under strong identification, our linear combination test has optimal power against local alternatives among the class of invariant or unbiased tests which are constructed based on jackknife AR and LM tests.
Learning Robust Recommender from Noisy Implicit Feedback
Inspired by this observation, we propose a new training strategy named Adaptive Denoising Training (ADT), which adaptively prunes the noisy interactions by two paradigms (i. e., Truncated Loss and Reweighted Loss).
Two Birds, One Stone: Achieving both Differential Privacy and Certified Robustness for Pre-trained Classifiers via Input Perturbation
To solve this challenge, a reconstruction network is built before the public pre-trained classifiers to offer certified robustness and defend against adversarial examples through input perturbation.
Wild Bootstrap for Instrumental Variables Regressions with Weak and Few Clusters
We study the wild bootstrap inference for instrumental variable regressions in the framework of a small number of large clusters in which the number of clusters is viewed as fixed and the number of observations for each cluster diverges to infinity.
FREE: Feature Refinement for Generalized Zero-Shot Learning
FREE employs a feature refinement (FR) module that incorporates \textit{semantic$\rightarrow$visual} mapping into a unified generative model to refine the visual features of seen and unseen class samples.
Certified Robustness to Word Substitution Attack with Differential Privacy
The robustness and security of natural language processing (NLP) models are significantly important in real-world applications.
Deconfounded Recommendation for Alleviating Bias Amplification
In this work, we scrutinize the cause-effect factors for bias amplification, identifying the main reason lies in the confounder effect of imbalanced item distribution on user representation and prediction score.
DyHCN: Dynamic Hypergraph Convolutional Networks
In general, DyHCN consists of a Hypergraph Convolution (HC) to encode the hypergraph structure at a time point and a Temporal Evolution module (TE) to capture the varying of the relations.
Market2Dish: Health-aware Food Recommendation
With the rising incidence of some diseases, such as obesity and diabetes, a healthy diet is arousing increasing attention.
Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue
However, we argue that there is a significant gap between clicks and user satisfaction -- it is common that a user is "cheated" to click an item by the attractive title/cover of the item.
Survival Modeling of Suicide Risk with Rare and Uncertain Diagnoses
Motivated by the pressing need for suicide prevention through improving behavioral healthcare, we use medical claims data to study the risk of subsequent suicide attempts for patients who were hospitalized due to suicide attempts and later discharged.
CDE-GAN: Cooperative Dual Evolution Based Generative Adversarial Network
In essence, CDE-GAN incorporates dual evolution with respect to the generator(s) and discriminators into a unified evolutionary adversarial framework to conduct effective adversarial multi-objective optimization.
Denoising Implicit Feedback for Recommendation
In this work, we explore the central theme of denoising implicit feedback for recommender training.
