Ruocheng Guo
YOU?
Author Swipe
View article: SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation Open
Knowledge Graphs (KGs) enhance recommender systems but face challenges from inherent noise, sparsity, and Euclidean geometry's inadequacy for complex relational structures, critically impairing representation learning, especially for long-…
View article: FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation
FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation Open
View article: STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation
STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation Open
View article: DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation
DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation Open
Neural Architecture Search (NAS) has emerged as a powerful approach for automating neural network design. However, existing NAS methods face critical limitations in real-world deployments: architectures lack adaptability across scenarios, …
View article: FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation
FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation Open
Modern recommendation systems face significant challenges in processing multimodal sequential data, particularly in temporal dynamics modeling and information flow coordination. Traditional approaches struggle with distribution discrepanci…
View article: STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation
STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation Open
Recent deep sequential recommendation models often struggle to effectively model key characteristics of user behaviors, particularly in handling sequence length variations and capturing diverse interaction patterns. We propose STAR-Rec, a …
View article: Optimal Policy Adaptation under Covariate Shift
Optimal Policy Adaptation under Covariate Shift Open
Transfer learning of prediction models has been extensively studied, while the corresponding policy learning approaches are rarely discussed. In this paper, we propose principled approaches for learning the optimal policy in the target dom…
View article: Stepwise Reasoning Disruption Attack of LLMs
Stepwise Reasoning Disruption Attack of LLMs Open
View article: Stepwise Reasoning Error Disruption Attack of LLMs
Stepwise Reasoning Error Disruption Attack of LLMs Open
Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain underexplored. Existing attacks on LLM reasoning are constrained by specific settings or la…
View article: DNS-Rec: Data-aware Neural Architecture Search for Recommender Systems
DNS-Rec: Data-aware Neural Architecture Search for Recommender Systems Open
View article: Conformal Counterfactual Inference under Hidden Confounding
Conformal Counterfactual Inference under Hidden Confounding Open
Personalized decision making requires the knowledge of potential outcomes under different treatments, and confidence intervals about the potential outcomes further enrich this decision-making process and improve its reliability in high-sta…
View article: Large Multimodal Model Compression via Iterative Efficient Pruning and Distillation
Large Multimodal Model Compression via Iterative Efficient Pruning and Distillation Open
The deployment of Large Multimodal Models (LMMs) within Ant Group has significantly advanced multimodal tasks in payment, security, and advertising, notably enhancing advertisement audition tasks in Alipay. However, the deployment of such …
View article: Media Bias Matters: Understanding the Impact of Politically Biased News on Vaccine Attitudes in Social Media
Media Bias Matters: Understanding the Impact of Politically Biased News on Vaccine Attitudes in Social Media Open
News media has been utilized as a political tool to stray from facts, presenting biased claims without evidence. Amid the COVID-19 pandemic, politically biased news (PBN) has significantly undermined public trust in vaccines, despite stron…
View article: Large Language Models for Data Annotation and Synthesis: A Survey
Large Language Models for Data Annotation and Synthesis: A Survey Open
Data annotation and synthesis generally refers to the labeling or generating of raw data with relevant information, which could be used for improving the efficacy of machine learning models. The process, however, is labor-intensive and cos…
View article: Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentation
Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentation Open
Graph contrastive learning (GCL) has emerged as a pivotal technique in the domain of graph representation learning. A crucial aspect of effective GCL is the caliber of generated positive and negative samples, which is intrinsically dictate…
View article: Cumulative Distribution Function based General Temporal Point Processes
Cumulative Distribution Function based General Temporal Point Processes Open
Temporal Point Processes (TPPs) hold a pivotal role in modeling event sequences across diverse domains, including social networking and e-commerce, and have significantly contributed to the advancement of recommendation systems and informa…
View article: DNS-Rec: Data-aware Neural Architecture Search for Recommender Systems
DNS-Rec: Data-aware Neural Architecture Search for Recommender Systems Open
In the era of data proliferation, efficiently sifting through vast information to extract meaningful insights has become increasingly crucial. This paper addresses the computational overhead and resource inefficiency prevalent in existing …
View article: SMLP4Rec: An Efficient All-MLP Architecture for Sequential Recommendations
SMLP4Rec: An Efficient All-MLP Architecture for Sequential Recommendations Open
Self-attention models have achieved the state-of-the-art performance in sequential recommender systems by capturing the sequential dependencies among user–item interactions. However, they rely on adding positional embeddings to the item se…
View article: Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup
Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup Open
The deployment of Large Multimodal Models (LMMs) within AntGroup has significantly advanced multimodal tasks in payment, security, and advertising, notably enhancing advertisement audition tasks in Alipay. However, the deployment of such s…
View article: Federated Knowledge Graph Completion via Latent Embedding Sharing and Tensor Factorization
Federated Knowledge Graph Completion via Latent Embedding Sharing and Tensor Factorization Open
Knowledge graphs (KGs), which consist of triples, are inherently incomplete and always require completion procedure to predict missing triples. In real-world scenarios, KGs are distributed across clients, complicating completion tasks due …
View article: Equal Opportunity of Coverage in Fair Regression
Equal Opportunity of Coverage in Fair Regression Open
We study fair machine learning (ML) under predictive uncertainty to enable reliable and trustworthy decision-making. The seminal work of ``equalized coverage'' proposed an uncertainty-aware fairness notion. However, it does not guarantee e…
View article: Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance
Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance Open
Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language Models (PLMs) have achieved substantial advancements in the field of natural language processing. However, in real-world scenarios, data labels are o…
View article: Embedding in Recommender Systems: A Survey
Embedding in Recommender Systems: A Survey Open
Recommender systems have become an essential component of many online platforms, providing personalized recommendations to users. A crucial aspect is embedding techniques that convert the high-dimensional discrete features, such as user an…
View article: Fair Classifiers that Abstain without Harm
Fair Classifiers that Abstain without Harm Open
In critical applications, it is vital for classifiers to defer decision-making to humans. We propose a post-hoc method that makes existing classifiers selectively abstain from predicting certain samples. Our abstaining classifier is incent…
View article: Deep Concept Removal
Deep Concept Removal Open
We address the problem of concept removal in deep neural networks, aiming to learn representations that do not encode certain specified concepts (e.g., gender etc.) We propose a novel method based on adversarial linear classifiers trained …
View article: Learning for Counterfactual Fairness from Observational Data
Learning for Counterfactual Fairness from Observational Data Open
Fairness-aware machine learning has attracted a surge of attention in many\ndomains, such as online advertising, personalized recommendation, and social\nmedia analysis in web applications. Fairness-aware machine learning aims to\neliminat…
View article: Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems
Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems Open
Data subsampling is widely used to speed up the training of large-scale recommendation systems. Most subsampling methods are model-based and often require a pre-trained pilot model to measure data importance via e.g. sample hardness. Howev…
View article: Inference-time Stochastic Ranking with Risk Control
Inference-time Stochastic Ranking with Risk Control Open
Learning to Rank (LTR) methods are vital in online economies, affecting users and item providers. Fairness in LTR models is crucial to allocate exposure proportionally to item relevance. Widely used deterministic LTR models can lead to unf…
View article: Virtual Node Tuning for Few-shot Node Classification
Virtual Node Tuning for Few-shot Node Classification Open
Few-shot Node Classification (FSNC) is a challenge in graph representation learning where only a few labeled nodes per class are available for training. To tackle this issue, meta-learning has been proposed to transfer structural knowledge…
View article: Tensorized Hypergraph Neural Networks
Tensorized Hypergraph Neural Networks Open
Hypergraph neural networks (HGNN) have recently become attractive and received significant attention due to their excellent performance in various domains. However, most existing HGNNs rely on first-order approximations of hypergraph conne…