Search Results for author: Evren Korpeoglu

Found 18 papers, 5 papers with code

LLMs with User-defined Prompts as Generic Data Operators for Reliable Data Processing

no code implementations26 Dec 2023 Luyi Ma, Nikhil Thakurdesai, Jiao Chen, Jianpeng Xu, Evren Korpeoglu, Sushant Kumar, Kannan Achan

Although the UDF design pattern introduces flexibility, reusability and scalability, the increasing demand on machine learning pipelines brings three new challenges to this design pattern -- not low-code, not dependency-free and not knowledge-aware.

GNN-GMVO: Graph Neural Networks for Optimizing Gross Merchandise Value in Similar Item Recommendation

no code implementations26 Oct 2023 Ramin Giahi, Reza Yousefi Maragheh, Nima Farrokhsiar, Jianpeng Xu, Jason Cho, Evren Korpeoglu, Sushant Kumar, Kannan Achan

Similar item recommendation is a critical task in the e-Commerce industry, which helps customers explore similar and relevant alternatives based on their interested products.

Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs

no code implementations17 May 2023 Jiao Chen, Luyi Ma, Xiaohan Li, Nikhil Thakurdesai, Jianpeng Xu, Jason H. D. Cho, Kaushiki Nag, Evren Korpeoglu, Sushant Kumar, Kannan Achan

Knowledge Graphs (KGs) play a crucial role in enhancing e-commerce system performance by providing structured information about entities and their relationships, such as complementary or substitutable relations between products or product types, which can be utilized in recommender systems.

Prompt Engineering Recommendation Systems +1

Causal Structure Learning with Recommendation System

no code implementations19 Oct 2022 Shuyuan Xu, Da Xu, Evren Korpeoglu, Sushant Kumar, Stephen Guo, Kannan Achan, Yongfeng Zhang

Discovering the causal mechanism from RS feedback data is both novel and challenging, since RS itself is a source of intervention that can influence both the users' exposure and their willingness to interact.

Decision Making Recommendation Systems

NEAT: A Label Noise-resistant Complementary Item Recommender System with Trustworthy Evaluation

no code implementations11 Feb 2022 Luyi Ma, Jianpeng Xu, Jason H. D. Cho, Evren Korpeoglu, Sushant Kumar, Kannan Achan

On the other hand, the model evaluation will not be trustworthy if the labels for evaluation are not reflecting the true complementary relatedness.

Recommendation Systems

Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives

no code implementations23 Oct 2021 Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan

The recent work by Rendle et al. (2020), based on empirical observations, argues that matrix-factorization collaborative filtering (MCF) compares favorably to neural collaborative filtering (NCF), and conjectures the dot product's superiority over the feed-forward neural network as similarity function.

Collaborative Filtering Transductive Learning

Towards the D-Optimal Online Experiment Design for Recommender Selection

1 code implementation23 Oct 2021 Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan

Selecting the optimal recommender via online exploration-exploitation is catching increasing attention where the traditional A/B testing can be slow and costly, and offline evaluations are prone to the bias of history data.

Multi-Armed Bandits

A Temporal Kernel Approach for Deep Learning with Continuous-time Information

2 code implementations ICLR 2021 Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan

Sequential deep learning models such as RNN, causal CNN and attention mechanism do not readily consume continuous-time information.

Density Estimation

Theoretical Understandings of Product Embedding for E-commerce Machine Learning

no code implementations24 Feb 2021 Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan

The generalization performance in the downstream machine learning task is controlled by the alignment between the embeddings and the product relatedness measure.

BIG-bench Machine Learning Dimensionality Reduction +2

GAN-based Recommendation with Positive-Unlabeled Sampling

no code implementations12 Dec 2020 Yao Zhou, Jianpeng Xu, Jun Wu, Zeinab Taghavi Nasrabadi, Evren Korpeoglu, Kannan Achan, Jingrui He

Recommender systems are popular tools for information retrieval tasks on a large variety of web applications and personalized products.

Generative Adversarial Network Information Retrieval +2

Adversarial Counterfactual Learning and Evaluation for Recommender System

1 code implementation NeurIPS 2020 Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan

The feedback data of recommender systems are often subject to what was exposed to the users; however, most learning and evaluation methods do not account for the underlying exposure mechanism.

Causal Inference counterfactual +1

Inductive Representation Learning on Temporal Graphs

4 code implementations ICLR 2020 Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan

Moreover, node and topological features can be temporal as well, whose patterns the node embeddings should also capture.

Graph Attention Graph Embedding +3

Self-attention with Functional Time Representation Learning

2 code implementations NeurIPS 2019 Da Xu, Chuanwei Ruan, Sushant Kumar, Evren Korpeoglu, Kannan Achan

To bridge the gap between modelling time-independent and time-dependent event sequence, we introduce a functional feature map that embeds time span into high-dimensional spaces.

Representation Learning Translation

Product Knowledge Graph Embedding for E-commerce

no code implementations28 Nov 2019 Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan

In this paper, we propose a new product knowledge graph (PKG) embedding approach for learning the intrinsic product relations as product knowledge for e-commerce.

Knowledge Graph Embedding Marketing +2

Knowledge-aware Complementary Product Representation Learning

no code implementations16 Mar 2019 Da Xu, Chuanwei Ruan, Jason Cho, Evren Korpeoglu, Sushant Kumar, Kannan Achan

Standard usage of representation learning emphasizes on only one set of embedding, which is problematic for modelling such properties of complementariness.

Multi-Task Learning Recommendation Systems +1

Generative Graph Convolutional Network for Growing Graphs

no code implementations6 Mar 2019 Da Xu, Chuanwei Ruan, Kamiya Motwani, Evren Korpeoglu, Sushant Kumar, Kannan Achan

Here we propose a unified generative graph convolutional network that learns node representations for all nodes adaptively in a generative model framework, by sampling graph generation sequences constructed from observed graph data.

Graph Generation Graph Reconstruction +1

Cannot find the paper you are looking for? You can Submit a new open access paper.