Search Results for author:
Found 86 papers, 43 papers with code
Multi-Scale Distribution Deep Variational Autoencoder for Explanation Generation
Generating explanations for recommender systems is essential for improving their transparency, as users often wish to understand the reason for receiving a specified recommendation.
Fact-Level Confidence Calibration and Self-Correction
Confidence calibration in LLMs, i. e., aligning their self-assessed confidence with the actual accuracy of their responses, enabling them to self-evaluate the correctness of their outputs.
Game-theoretic LLM: Agent Workflow for Negotiation Games
This paper investigates the rationality of large language models (LLMs) in strategic decision-making contexts, specifically within the framework of game theory.
KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold Networks
Due to the common occurrence of noise, i. e., local peaks and drops in time series, existing black-box learning methods can easily learn these unintended patterns, significantly affecting anomaly detection performance.
Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
Adversarial Collaborative Filtering (ACF), which typically applies adversarial perturbations at user and item embeddings through adversarial training, is widely recognized as an effective strategy for enhancing the robustness of Collaborative Filtering (CF) recommender systems against poisoning attacks.
Pruning Foundation Models for High Accuracy without Retraining
To deal with this problem, post-training pruning methods are proposed to prune LLMs in one-shot without retraining.
MITA: Bridging the Gap between Model and Data for Test-time Adaptation
Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models.
Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System
Leveraging these insights, we introduce the Vulnerability-aware Adversarial Training (VAT), designed to defend against poisoning attacks in recommender systems.
Accelerating the Surrogate Retraining for Poisoning Attacks against Recommender Systems
Recent studies have demonstrated the vulnerability of recommender systems to data poisoning attacks, where adversaries inject carefully crafted fake user interactions into the training data of recommenders to promote target items.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #2 on
Multi-task Language Understanding
on MMLU
Understanding the Collapse of LLMs in Model Editing
Despite significant progress in model editing methods, their application in real-world scenarios remains challenging as they often cause large language models (LLMs) to collapse.
Is Flash Attention Stable?
Training large-scale machine learning models poses distinct system challenges, given both the size and complexity of today's workloads.
When to Trust LLMs: Aligning Confidence with Response Quality
Specifically, the order-preserving reward incentivizes the model to verbalize greater confidence for responses of higher quality to align the order of confidence and quality.
Unlink to Unlearn: Simplifying Edge Unlearning in GNNs
As concerns over data privacy intensify, unlearning in Graph Neural Networks (GNNs) has emerged as a prominent research frontier in academia.
The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse
In this work, we reveal a critical phenomenon: even a single edit can trigger model collapse, manifesting as significant performance degradation in various benchmark tasks.
LoRec: Large Language Model for Robust Sequential Recommendation against Poisoning Attacks
Traditional defense strategies predominantly depend on predefined assumptions or rules extracted from specific known attacks, limiting their generalizability to unknown attack types.
Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
While auxiliary information has become a key to enhancing Large Language Models (LLMs), relatively little is known about how LLMs merge these contexts, specifically contexts generated by LLMs and those retrieved from external sources.
Generative AI Beyond LLMs: System Implications of Multi-Modal Generation
As the development of large-scale Generative AI models evolve beyond text (1D) generation to include image (2D) and video (3D) generation, processing spatial and temporal information presents unique challenges to quality, performance, and efficiency.
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
On segment anything task such as zero-shot instance segmentation, our EfficientSAMs with SAMI-pretrained lightweight image encoders perform favorably with a significant gain (e. g., ~4 AP on COCO/LVIS) over other fast SAM models.
Ranked #3 on
Zero-Shot Instance Segmentation
on LVIS v1.0 val
TEA: Test-time Energy Adaptation
To address this, we propose a novel energy-based perspective, enhancing the model's perception of target data distributions without requiring access to training data or processes.
Robust Recommender System: A Survey and Future Directions
With the rapid growth of information, recommender systems have become integral for providing personalized suggestions and overcoming information overload.
A Large Language Model Enhanced Conversational Recommender System
For response generation, we utilize the generation ability of LLM as a language interface to better interact with users.
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
In NLP tasks like machine translation and pre-trained language modeling, there is a significant performance gap between supernet and training from scratch for the same model architecture, necessitating retraining post optimal architecture identification.
PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion
The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones.
Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets
Firstly, we address the oversimplified heterogeneity settings of current datasets and propose two new HHKG datasets that closely mimic practical EA scenarios.
LegoNet: A Fast and Exact Unlearning Architecture
However, such a strategy typically leads to a loss in model performance, which poses the challenge that increasing the unlearning efficiency while maintaining acceptable performance.
MILAN: Masked Image Pretraining on Language Assisted Representation
When the masked autoencoder is pretrained and finetuned on ImageNet-1K dataset with an input resolution of 224x224, MILAN achieves a top-1 accuracy of 85. 4% on ViT-Base, surpassing previous state-of-the-arts by 1%.
Adversarial Camouflage for Node Injection Attack on Graphs
In this paper, we first propose and define camouflage as distribution similarity between ego networks of injected nodes and normal nodes.
Debiasing Learning for Membership Inference Attacks Against Recommender Systems
To address the above limitations, we propose a Debiasing Learning for Membership Inference Attacks against recommender systems (DL-MIA) framework that has four main components: (1) a difference vector generator, (2) a disentangled encoder, (3) a weight estimator, and (4) an attack model.
Studying the Impact of Data Disclosure Mechanism in Recommender Systems via Simulation
Then we study users' privacy decision making under different data disclosure mechanisms and recommendation models, and how their data disclosure decisions affect the recommender system's performance.
CHEX: CHannel EXploration for CNN Model Compression
However, conventional pruning methods have limitations in that: they are restricted to pruning process only, and they require a fully pre-trained large model.
Neural Re-ranking in Multi-stage Recommender Systems: A Review
As the final stage of the multi-stage recommender system (MRS), re-ranking directly affects user experience and satisfaction by rearranging the input ranking lists, and thereby plays a critical role in MRS. With the advances in deep learning, neural re-ranking has become a trending topic and been widely applied in industrial applications.
Recommendation Unlearning
From the perspective of utility, if a system's utility is damaged by some bad data, the system needs to forget these data to regain utility.
Compact Multi-level Sparse Neural Networks with Input Independent Dynamic Rerouting
Deep neural networks (DNNs) have shown to provide superb performance in many real life applications, but their large computation cost and storage requirement have prevented them from being deployed to many edge and internet-of-things (IoT) devices.
Load-balanced Gather-scatter Patterns for Sparse Deep Neural Networks
Our experiments show that GS patterns consistently make better trade-offs between accuracy and computation efficiency compared to conventional structured sparse patterns.
Counterfactual Evaluation for Explainable AI
While recent years have witnessed the emergence of various explainable methods in machine learning, to what degree the explanations really represent the reasoning process behind the model prediction -- namely, the faithfulness of explanation -- is still an open problem.
Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation
However, existing metrics either neglect the intrinsic cause of the factual inconsistency or rely on auxiliary tasks, leading to an unsatisfied correlation with human judgments or increasing the inconvenience of usage in practice.
Effective Model Sparsification by Scheduled Grow-and-Prune Methods
It addresses the shortcomings of the previous works by repeatedly growing a subset of layers to dense and then pruning them back to sparse after some training.
CausCF: Causal Collaborative Filtering for RecommendationEffect Estimation
It is based on the idea that similar users not only have a similar taste on items, but also have similar treatment effect under recommendations.
Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning
However, existing methods mainly target at solving one or two of these three decision-making problems in CRS with separated conversation and recommendation components, which restrict the scalability and generality of CRS and fall short of preserving a stable training procedure.
GRN: Generative Rerank Network for Context-wise Recommendation
Specifically, we first design the evaluator, which applies Bi-LSTM and self-attention mechanism to model the contextual information in the labeled final ranking list and predict the interaction probability of each item more precisely.
Semantic Models for the First-stage Retrieval: A Comprehensive Review
We believe it is the right time to survey current status, learn from existing methods, and gain some insights for future development.
Explore User Neighborhood for Real-time E-commerce Recommendation
On the one hand, it utilizes UI relations and user neighborhood to capture both global and local information.
Variation Control and Evaluation for Generative SlateRecommendations
Slate recommendation generates a list of items as a whole instead of ranking each item individually, so as to better model the intra-list positional biases and item relations.
Revisit Recommender System in the Permutation Prospective
Afterwards, for the candidate list set, the PRank stage provides a unified permutation-wise ranking criterion named LR metric, which is calculated by the rating scores of elaborately designed permutation-wise model DPWN.
Graph Attention Collaborative Similarity Embedding for Recommender System
We present Graph Attention Collaborative Similarity Embedding (GACSE), a new recommendation framework that exploits collaborative information in the user-item bipartite graph for representation learning.
Towards Long-term Fairness in Recommendation
We focus on the fairness of exposure of items in different groups, while the division of the groups is based on item popularity, which dynamically changes over time in the recommendation process.
CLEAR: Contrastive Learning for Sentence Representation
Pre-trained language models have proven their unique powers in capturing implicit language features.
Ranked #5 on
Question Answering
on Quora Question Pairs
Graph Neural Networks in Recommender Systems: A Survey
With the explosive growth of online information, recommender systems play a key role to alleviate such information overload.
Contrastive Learning for Sequential Recommendation
Sequential recommendation methods play a crucial role in modern recommender systems because of their ability to capture a user's dynamic interest from her/his historical interactions.
XDM: Improving Sequential Deep Matching with Unclicked User Behaviors for Recommender System
The offline experimental results based on real-world E-commerce data demonstrate the effectiveness and verify the importance of unclicked items in sequential recommendation.
NGAT4Rec: Neighbor-Aware Graph Attention Network For Recommendation
To modeling the implicit correlations of neighbors in graph embedding aggregating, we propose a Neighbor-Aware Graph Attention Network for recommendation task, termed NGAT4Rec.
MTBRN: Multiplex Target-Behavior Relation Enhanced Network for Click-Through Rate Prediction
In this paper, we propose a new framework named Multiplex Target-Behavior Relation enhanced Network (MTBRN) to leverage multiplex relations between user behaviors and target item to enhance CTR prediction.
Ranking Enhanced Dialogue Generation
To tackle this problem, we propose a Ranking Enhanced Dialogue generation framework in this paper.
Learning Personalized Risk Preferences for Recommendation
Before making purchases on e-commerce websites, most consumers tend to rely on rating scores and review information to make purchase decisions.
Understanding Echo Chambers in E-commerce Recommender Systems
Current research on recommender systems mostly focuses on matching users with proper items based on user interests.
Computation on Sparse Neural Networks: an Inspiration for Future Hardware
We show that for practically complicated problems, it is more beneficial to search large and sparse models in the weight dominated region.
A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods
To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categories, i. e., static regularization-based pruning and dynamic regularization-based pruning.
Complex risk statistics with scenario analysis
Complex risk is a critical factor for both intelligent systems and risk management.
Skeleton Based Action Recognition using a Stacked Denoising Autoencoder with Constraints of Privileged Information
Differing from the previous studies, we propose a new method called Denoising Autoencoder with Temporal and Categorical Constraints (DAE_CTC)} to study the skeletal representation in a view of skeleton reconstruction.
Learning in the Frequency Domain
Experiment results show that learning in the frequency domain with static channel selection can achieve higher accuracy than the conventional spatial downsampling approach and meanwhile further reduce the input data size.
SDM: Sequential Deep Matching Model for Online Large-scale Recommender System
In this paper, we propose a new sequential deep matching (SDM) model to capture users' dynamic preferences by combining short-term sessions and long-term behaviors.
Privileged Features Distillation at Taobao Recommendations
To guarantee the consistency of off-line training and on-line serving, we usually utilize the same features that are both available.
Improving Multi-turn Dialogue Modelling with Utterance ReWriter
To properly train the utterance rewriter, we collect a new dataset with human annotations and introduce a Transformer-based utterance rewriting architecture using the pointer network.
Exact-K Recommendation via Maximal Clique Optimization
This paper targets to a novel but practical recommendation problem named exact-K recommendation.
Deep Session Interest Network for Click-Through Rate Prediction
Easy-to-use, Modular and Extendible package of deep-learning based CTR models. DeepFM, DeepInterestNetwork(DIN), DeepInterestEvolutionNetwork(DIEN), DeepCrossNetwork(DCN), AttentionalFactorizationMachine(AFM), Neural Factorization Machine(NFM), AutoInt, Deep Session Interest Network(DSIN)
POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion
In particular, there exist two requirements for fashion outfit recommendation: the Compatibility of the generated fashion outfits, and the Personalization in the recommendation process.
Strain engineering of epitaxial oxide heterostructures beyond substrate limitations
The limitation of commercially available single-crystal substrates and the lack of continuous strain tunability preclude the ability to take full advantage of strain engineering for further exploring novel properties and exhaustively studying fundamental physics in complex oxides.
Materials Science
Compositional Network Embedding
Node ID is not generalizable and, thus, the existing methods have to pay great effort in cold-start problem.
Regulator-based risk statistics with scenario analysis
As regulators pay more attentions to losses rather than gains, we are able to derive a new class of risk statistics, named regulator-based risk statistics with scenario analysis in this paper.
Regulator-based risk statistics for portfolios
Risk statistic is a critical factor not only for risk analysis but also for financial application.
Set-valued risk statistics with the time value of money
The time value of money is a critical factor not only in risk analysis, but also in insurance and financial applications.
Low-Power Computer Vision: Status, Challenges, Opportunities
In addition to mobile phones, many autonomous systems rely on visual data for making decisions and some of these systems have limited energy (such as unmanned aerial vehicles also called drones and mobile robots).
Personalized Re-ranking for Recommendation
Ranking is a core task in recommender systems, which aims at providing an ordered list of items to users.
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
To address this problem, we train the bidirectional model using the Cloze task, predicting the masked items in the sequence by jointly conditioning on their left and right context.
Ranked #3 on
Recommendation Systems
on MovieLens 1M
(HR@10 (full corpus) metric)
Value-aware Recommendation based on Reinforced Profit Maximization in E-commerce Systems
Existing recommendation algorithms mostly focus on optimizing traditional recommendation measures, such as the accuracy of rating prediction in terms of RMSE or the quality of top-$k$ recommendation lists in terms of precision, recall, MAP, etc.
ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation
We formulate platform-aware NN architecture search in an optimization framework and propose a novel algorithm to search for optimal architectures aided by efficient accuracy and resource (latency and/or energy) predictors.
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
Due to this, previous neural architecture search (NAS) methods are computationally expensive.
Ranked #946 on
Image Classification
on ImageNet
2018 Low-Power Image Recognition Challenge
The Low-Power Image Recognition Challenge (LPIRC, https://rebootingcomputing. ieee. org/lpirc) is an annual competition started in 2015.
Multi-Source Pointer Network for Product Title Summarization
For the second constraint, we restore the key information by copying words from the knowledge encoder with the help of the soft gating mechanism.
Dynamic risk measures with fluctuation of market volatility under Bochne-Lebesgue space
Starting from the global financial crisis to the more recent disruptions brought about by geopolitical tensions and public health crises, the volatility of risk in financial markets has increased significantly.
Semantic Regularities in Document Representations
Recent work exhibited that distributed word representations are good at capturing linguistic regularities in language.
Component-Enhanced Chinese Character Embeddings
Distributed word representations are very useful for capturing semantic information and have been successfully applied in a variety of NLP tasks, especially on English.
