Search Results for author:
Found 113 papers, 55 papers with code
Matching-oriented Embedding Quantization For Ad-hoc Retrieval
In this work, we propose the Matching-oriented Product Quantization (MoPQ), where a novel objective Multinoulli Contrastive Loss (MCL) is formulated.
Scaling New Frontiers: Insights into Large Recommendation Models
In this paper, we aim to enhance the understanding of scaling laws by conducting comprehensive evaluations of large recommendation models.
Predictive Models in Sequential Recommendations: Bridging Performance Laws with Data Quality Insights
In response, we introduce the Performance Law for SR models, which aims to theoretically investigate and model the relationship between model performance and data quality.
Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction
Recent advancements have shown that modeling rich user behaviors can significantly improve the performance of CTR prediction.
TDDBench: A Benchmark for Training data detection
Training Data Detection (TDD) is a task aimed at determining whether a specific data instance is used to train a machine learning model.
FilterNet: Harnessing Frequency Filters for Time Series Forecasting
While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting.
Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model
Sequential recommendation (SR) aims to predict items that users may be interested in based on their historical behavior sequences.
RecFlow: An Industrial Full Flow Recommendation Dataset
Industrial recommendation systems (RS) rely on the multi-stage pipeline to balance effectiveness and efficiency when delivering items from a vast corpus to users.
Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing
In the work, we focus on utilizing LLMs to perform machine translation, where we observe that two patterns of errors frequently occur and drastically affect the translation quality: language mismatch and repetition.
MDAP: A Multi-view Disentangled and Adaptive Preference Learning Framework for Cross-Domain Recommendation
Cross-domain Recommendation systems leverage multi-domain user interactions to improve performance, especially in sparse data or new user scenarios.
Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation
In this approach, the retrieved contexts are compressed into compact embeddings before being encoded by the LLMs.
Making Text Embedders Few-Shot Learners
To this end, we introduce a novel model bge-en-icl, which employs few-shot examples to produce high-quality text embeddings.
ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models
To this end, we propose \textbf{\textit{ChemEval}}, which provides a comprehensive assessment of the capabilities of LLMs across a wide range of chemical domain tasks.
ToolACE: Winning the Points of LLM Function Calling
Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability.
Efficient Transfer Learning Framework for Cross-Domain Click-Through Rate Prediction
The challenges include the inefficiencies arising from the management of extensive source data and the problem of 'catastrophic forgetting' that results from the CTR model's daily updating.
DimeRec: A Unified Framework for Enhanced Sequential Recommendation via Generative Diffusion Models
Nevertheless, a straightforward combination of SR and DM leads to sub-optimal performance due to discrepancies in learning objectives (recommendation vs. noise reconstruction) and the respective learning spaces (non-stationary vs. stationary).
Denoising Pre-Training and Customized Prompt Learning for Efficient Multi-Behavior Sequential Recommendation
Its objective is to extract knowledge from extensive pre-training data and fine-tune the model for downstream tasks.
Learning Deep Tree-based Retriever for Efficient Recommendation: Theory and Method
Although advancements in deep learning have significantly enhanced the recommendation accuracy of deep recommendation models, these methods still suffer from low recommendation efficiency.
Multi-agent Multi-armed Bandits with Stochastic Sharable Arm Capacities
We also design an iterative distributed algorithm for players to commit to an optimal arm pulling profile with a constant number of rounds in expectation.
Analytical and Empirical Study of Herding Effects in Recommendation Systems
We also study the speed of convergence numerically and reveal trade-offs in selecting rating aggregation rules and review selection mechanisms.
DaRec: A Disentangled Alignment Framework for Large Language Model and Recommender System
In this work, we prove that directly aligning the representations of LLMs and collaborative models is sub-optimal for enhancing downstream recommendation tasks performance, based on the information theorem.
Dual Test-time Training for Out-of-distribution Recommender System
To address this challenge, we propose a novel Dual Test-Time-Training framework for OOD Recommendation, termed DT3OR.
Entropy Law: The Story Behind Data Compression and LLM Performance
Inspired by the information compression nature of LLMs, we uncover an ``entropy law'' that connects LLM performance with data compression ratio and first-epoch training loss, which reflect the information redundancy of a dataset and the mastery of inherent knowledge encoded in this dataset, respectively.
Foundations and Frontiers of Graph Learning Theory
Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures.
Refine Large Language Model Fine-tuning via Instruction Vector
Fine-tuning large language models (LLMs) can cause them to lose their general capabilities.
Mitigate Negative Transfer with Similarity Heuristic Lifelong Prompt Tuning
Lifelong prompt tuning has significantly advanced parameter-efficient lifelong learning with its efficiency and minimal storage demands on various tasks.
Exploring User Retrieval Integration towards Large Language Models for Cross-Domain Sequential Recommendation
To this end, we propose a novel framework named URLLM, which aims to improve the CDSR performance by exploring the User Retrieval approach and domain grounding on LLM simultaneously.
PRICE: A Pretrained Model for Cross-Database Cardinality Estimation
It is generally applicable to any unseen new database to attain high estimation accuracy, while its preparation cost is as little as the basic one-dimensional histogram-based CardEst methods.
Dataset Regeneration for Sequential Recommendation
The sequential recommender (SR) system is a crucial component of modern recommender systems, as it aims to capture the evolving preferences of users.
Learning Partially Aligned Item Representation for Cross-Domain Sequential Recommendation
Cross-domain sequential recommendation (CDSR) aims to uncover and transfer users' sequential preferences across multiple recommendation domains.
CELA: Cost-Efficient Language Model Alignment for CTR Prediction
This model-agnostic framework can be equipped with plug-and-play textual features, with item-level alignment enhancing the utilization of external information while maintaining training and inference efficiency.
UniDM: A Unified Framework for Data Manipulation with Large Language Models
In this paper, inspired by the cross-task generality of LLMs on NLP tasks, we pave the first step to design an automatic and general solution to tackle with data manipulation tasks.
Evaluating Readability and Faithfulness of Concept-based Explanations
Based on this, we quantify the faithfulness of a concept explanation via perturbation.
Understanding Privacy Risks of Embeddings Induced by Large Language Models
Large language models (LLMs) show early signs of artificial general intelligence but struggle with hallucinations.
WESE: Weak Exploration to Strong Exploitation for LLM Agents
Concretely, WESE involves decoupling the exploration and exploitation process, employing a cost-effective weak agent to perform exploration tasks for global knowledge.
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text generation (MCTG) methods.
A Unified Framework for Adaptive Representation Enhancement and Inversed Learning in Cross-Domain Recommendation
To this end, we propose a Unified Framework for Adaptive Representation Enhancement and Inversed Learning in Cross-Domain Recommendation (AREIL).
END4Rec: Efficient Noise-Decoupling for Multi-Behavior Sequential Recommendation
In recommendation systems, users frequently engage in multiple types of behaviors, such as clicking, adding to a cart, and purchasing.
Cross-Domain Pre-training with Language Models for Transferable Time Series Representations
To address this challenge, we propose CrossTimeNet, a novel cross-domain SSL learning framework to learn transferable knowledge from various domains to largely benefit the target downstream task.
Re-Search for The Truth: Multi-round Retrieval-augmented Large Language Models are Strong Fake News Detectors
The proliferation of fake news has had far-reaching implications on politics, the economy, and society at large.
NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation
Hence, NoiseDiffusion performs interpolation within the noisy image space and injects raw images into these noisy counterparts to address the challenge of information loss.
Aligning Language Models for Versatile Text-based Item Retrieval
Our empirical studies demonstrate that fine-tuning embedding models on the dataset leads to remarkable improvements in a variety of retrieval tasks.
Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users
We study the problem of federated contextual combinatorial cascading bandits, where $|\mathcal{U}|$ agents collaborate under the coordination of a central server to provide tailored recommendations to the $|\mathcal{U}|$ corresponding users.
Understanding and Patching Compositional Reasoning in LLMs
LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks.
BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval, which provides a unified model foundation for real-world IR applications.
Understanding the planning of LLM agents: A survey
As Large Language Models (LLMs) have shown significant intelligence, the progress to leverage LLMs as planning modules of autonomous agents has attracted more attention.
Securing Recommender System via Cooperative Training
Consequently, we put forth a Game-based Co-training Attack (GCoAttack), which frames the proposed CoAttack and TCD as a game-theoretic process, thoroughly exploring CoAttack's attack potential in the cooperative training of attack and defense.
Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity
Recent research demonstrates that GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions.
Model Stealing Attack against Recommender System
Some adversarial attacks have achieved model stealing attacks against recommender systems, to some extent, by collecting abundant training data of the target model (target data) or making a mass of queries.
Invariant Representation via Decoupling Style and Spurious Features from Images
This paper considers the out-of-distribution (OOD) generalization problem under the setting that both style distribution shift and spurious features exist and domain labels are missing.
AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction
Most existing methods focus on the network architecture design of the CTR model for better accuracy and suffer from the data sparsity problem.
RecExplainer: Aligning Large Language Models for Explaining Recommendation Models
Behavior alignment operates in the language space, representing user preferences and item information as text to mimic the target model's behavior; intention alignment works in the latent space of the recommendation model, using user and item representations to understand the model's behavior; hybrid alignment combines both language and latent spaces.
Deep Group Interest Modeling of Full Lifelong User Behaviors for CTR Prediction
The insights from this subset reveal the user's decision-making process related to the candidate item, improving prediction accuracy.
Frequency-domain MLPs are More Effective Learners in Time Series Forecasting
FreTS mainly involves two stages, (i) Domain Conversion, that transforms time-domain signals into complex numbers of frequency domain; (ii) Frequency Learning, that performs our redesigned MLPs for the learning of real and imaginary part of frequency components.
APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation
To this end, we propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR), that incorporates adaptive and personalized global collaborative information into sequential recommendation systems.
Batch-Mix Negative Sampling for Learning Recommendation Retrievers
Recommendation retrievers commonly retrieve user potentially preferred items from numerous items, where the query and item representation are learned according to the dual encoders with the log-softmax loss.
A Data-Centric Multi-Objective Learning Framework for Responsible Recommendation Systems
Recommendation systems effectively guide users in locating their desired information within extensive content repositories.
Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt
In this work, we first investigate such anytime fine-tuning effectiveness of existing continual pre-training approaches, concluding with unanimously decreased performance on unseen domains.
Large-Scale OD Matrix Estimation with A Deep Learning Method
To alleviate this problem, some researchers incorporate a prior OD matrix as a target in the regression to provide more structural constraints.
Toward Robust Recommendation via Real-time Vicinal Defense
Recommender systems have been shown to be vulnerable to poisoning attacks, where malicious data is injected into the dataset to cause the recommender system to provide biased recommendations.
Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias
The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction
This implies the great potential of the semantic correlations for the entity-independent inductive link prediction task.
C-Pack: Packed Resources For General Chinese Embeddings
Along with our resources on general Chinese embedding, we release our data and models for English text embeddings.
Interactive Graph Convolutional Filtering
Furthermore, we employ Bayesian meta-learning methods to effectively address the cold-start problem and derive theoretical regret bounds for our proposed method, ensuring a robust performance guarantee.
Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations
In this paper, we bridge the gap between recommender models and LLMs, combining their respective strengths to create a versatile and interactive recommender system.
KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification
However, the multi-faceted semantic orientation in the feature-semantic alignment has been neglected by previous work, i. e. the content of a node usually covers diverse topics that are relevant to the semantics of multiple labels.
Deep Task-specific Bottom Representation Network for Multi-Task Recommendation
In this paper, we focus on the bottom representation learning of MTL in RS and propose the Deep Task-specific Bottom Representation Network (DTRN) to alleviate the negative transfer problem.
When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities
The advent of large language models marks a revolutionary breakthrough in artificial intelligence.
A DeepLearning Framework for Dynamic Estimation of Origin-Destination Sequence
To this end, this paper proposes an integrated method, which uses deep learning methods to infer the structure of OD sequence and uses structural constraints to guide traditional numerical optimization.
Learning to Substitute Spans towards Improving Compositional Generalization
Despite the rising prevalence of neural sequence models, recent empirical evidences suggest their deficiency in compositional generalization.
Provably Convergent Subgraph-wise Sampling for Fast GNN Training
During the message passing (MP) in GNNs, subgraph-wise sampling methods discard messages outside the mini-batches in backward passes to avoid the well-known neighbor explosion problem, i. e., the exponentially increasing dependencies of nodes with the number of MP iterations.
Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors
We only provide vehicle count data from spatially sparse stationary vehicle detectors in these three cities as model input for this task.
GUESR: A Global Unsupervised Data-Enhancement with Bucket-Cluster Sampling for Sequential Recommendation
Sequential Recommendation is a widely studied paradigm for learning users' dynamic interests from historical interactions for predicting the next potential item.
Improving Recommendation Fairness via Data Augmentation
We augment imbalanced training data towards balanced data distribution to improve fairness.
Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation
Recent studies show that Graph Neural Networks(GNNs) are vulnerable and easily fooled by small perturbations, which has raised considerable concerns for adapting GNNs in various safety-critical applications.
Transposed Variational Auto-encoder with Intrinsic Feature Learning for Traffic Forecasting
In this technical report, we present our solutions to the Traffic4cast 2022 core challenge and extended challenge.
Towards Robust Recommender Systems via Triple Cooperative Defense
Notably, TCD adds pseudo label data instead of deleting abnormal data, which avoids the cleaning of normal data, and the cooperative training of the three models is also beneficial to model generalization.
Cooperative Retriever and Ranker in Deep Recommenders
Deep recommender systems (DRS) are intensively applied in modern web services.
Boosting Factorization Machines via Saliency-Guided Mixup
Second, considering that MixFM may generate redundant or even detrimental instances, we further put forward a novel Factorization Machine powered by Saliency-guided Mixup (denoted as SMFM).
Cache-Augmented Inbatch Importance Resampling for Training Recommender Retriever
Recommender retrievers aim to rapidly retrieve a fraction of items from the entire item corpus when a user query requests, with the representative two-tower model trained with the log softmax loss.
Self-Supervised Text Erasing with Controllable Image Synthesis
The synthetic training images with erasure ground-truth are then fed to train a coarse-to-fine erasing network.
BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction
Regarding missing link inference of diverse networks, we revisit the link prediction techniques and identify the importance of both the structural and attribute information.
HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization
Hyperbolic space offers a spacious room to learn embeddings with its negative curvature and metric properties, which can well fit data with tree-like structures.
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings
We perform comprehensive explorations for the optimal conduct of knowledge distillation, which may provide useful insights for the learning of VQ based ANN index.
Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics
Current practices in metric evaluation focus on one single dataset, e. g., Newstest dataset in each year's WMT Metrics Shared Task.
Visualizing the Relationship Between Encoded Linguistic Information and Task Performance
To this end, we study the dynamic relationship between the encoded linguistic information and task performance from the viewpoint of Pareto Optimality.
A Mutually Reinforced Framework for Pretrained Sentence Embeddings
Instead of relying on annotation heuristics defined by humans, it leverages the sentence representation model itself and realizes the following iterative self-supervision process: on one hand, the improvement of sentence representation may contribute to the quality of data annotation; on the other hand, more effective data annotation helps to generate high-quality positive samples, which will further improve the current sentence representation model.
Reinforcement Routing on Proximity Graph for Efficient Recommendation
Instead of searching the nearest neighbor for the query, we search the item with maximum inner product with query on the proximity graph.
Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval
In this work, we tackle this problem with Bi-Granular Document Representation, where the lightweight sparse embeddings are indexed and standby in memory for coarse-grained candidate search, and the heavyweight dense embeddings are hosted in disk for fine-grained post verification.
Meta-learning with an Adaptive Task Scheduler
In ATS, for the first time, we design a neural scheduler to decide which meta-training tasks to use next by predicting the probability being sampled for each candidate task, and train the scheduler to optimize the generalization capacity of the meta-model to unseen tasks.
Learned Index with Dynamic $\epsilon$
We theoretically analyze prediction error bounds that link $\epsilon$ with data characteristics for an illustrative learned index method.
Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering
Variational AutoEncoder (VAE) has been extended as a representative nonlinear method for collaborative filtering.
Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention
With the rapid development of these services in the last two decades, users have accumulated a massive amount of behavior data.
Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation
Inspired by the idea of vector quantization that uses cluster centroids to approximate items, we propose LISA (LInear-time Self Attention), which enjoys both the effectiveness of vanilla self-attention and the efficiency of sparse attention.
GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph
The representation learning on textual graph is to generate low-dimensional embeddings for the nodes based on the individual textual features and the neighbourhood information.
Assessing Dialogue Systems with Distribution Distances
An important aspect of developing dialogue systems is how to evaluate and compare the performance of different systems.
A Unified Transferable Model for ML-Enhanced DBMS
We propose to explore the transferabilities of the ML methods both across tasks and across DBs to tackle these fundamental drawbacks.
Hybrid Encoder: Towards Efficient and Precise Native AdsRecommendation via Hybrid Transformer Encoding Networks
For the sake of efficient recommendation, conventional methods would generate user and advertisement embeddings independently with a siamese transformer encoder, such that approximate nearest neighbour search (ANN) can be leveraged.
Matching-oriented Product Quantization For Ad-hoc Retrieval
In this work, we propose the Matching-oriented Product Quantization (MoPQ), where a novel objective Multinoulli Contrastive Loss (MCL) is formulated.
Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure
Based on the tree structure, Thompson sampling is adapted with dynamic programming, leading to efficient exploration for potential ad creatives with the largest CTR.
Automated Creative Optimization for E-Commerce Advertising
However, interactions between creative elements may be more complex than the inner product, and the FM-estimated CTR may be of high variance due to limited feedback.
A Hybrid Bandit Model with Visual Priors for Creative Ranking in Display Advertising
Creative plays a great important role in e-commerce for exhibiting products.
Deep Pairwise Hashing for Cold-start Recommendation
Specifically, we first pre-train robust item representation from item content data by a Denoising Auto-encoder instead of other deterministic deep learning frameworks; then we finetune the entire framework by adding a pairwise loss objective with discrete constraints; moreover, DPH aims to minimize a pairwise ranking loss that is consistent with the ultimate goal of recommendation.
Sampling-Decomposable Generative Adversarial Recommender
The GAN-style recommenders (i. e., IRGAN) addresses the challenge by learning a generator and a discriminator adversarially, such that the generator produces increasingly difficult samples for the discriminator to accelerate optimizing the discrimination objective.
Learning to Transfer Graph Embeddings for Inductive Graph based Recommendation
The transfer network is designed to approximate the learned item embeddings from graph neural networks by taking each item's visual content as input, in order to tackle the new segment problem in the test phase.
GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactions
We observe that existing works on structured entity interaction prediction cannot properly exploit the unique graph of graphs model.
Lightrec: A memory and search-efficient recommender system
On top of such a structure, LightRec will have an item represented as additive composition of B codewords, which are optimally selected from each of the codebooks.
Binarized Graph Neural Network
Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches to binarize the model parameters and learn the compact embedding.
A Novel User Representation Paradigm for Making Personalized Candidate Retrieval
Our work is undergoing a anonymous review, and it will soon be released after the notification.
Binarized Collaborative Filtering with Distilling Graph Convolutional Networks
Then we distill the ranking information derived from GCN into binarized collaborative filtering, which makes use of binary representation to improve the efficiency of online recommendation.
MCNE: An End-to-End Framework for Learning Multiple Conditional Network Representations of Social Network
Recently, the Network Representation Learning (NRL) techniques, which represent graph structure via low-dimension vectors to support social-oriented application, have attracted wide attention.
A Survey on Session-based Recommender Systems
In recent years, session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs.
Binarized Attributed Network Embedding
To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation.
Ranked #1 on
Link Prediction
on Wiki
