Recommender system (RecSys) plays important roles in helping users navigate, discover, and consume massive and highly-dynamic information. Today, many RecSys solutions deployed in the real world rely on categorical user profiles and/or pre-calculated recommendation actions that stay static during a user session. However, recent trends suggest that RecSys need to model user intent in real time and constantly adapt to meet user needs at the moment or change user behavior in situ. There are three primary drivers for this emerging need of online adaptation. First, in order to meet the increasing demand for a better personalized experience, the personalization dimensions and space will grow larger and larger. It would not be feasible to pre-compute recommended actions for all personalization scenarios beyond a certain scale. Second, in many settings the system does not have user prior history to leverage. Estimating user intent in real time is the only way to personalize. As various consumer privacy laws tighten, it is foreseeable that many businesses will reduce their reliance on static user profiles. Therefore, it makes the modeling of user intent in real time an important research topic. Third, a user's intent often changes within a session and between sessions, and user behavior could shift significantly during dramatic events. Therefore, it is important to investigate more on online and adaptive recommender systems (OARS) that can adapt in real time to meet user needs and be robust against distribution shifts. Every year, the organizers survey the most important topics for OARS and propose a new workshop program. In light of the recent advancement of (multi-modal) LLMs in RecSys, in this new edition, we decide to formally add the new topic of (multi-modal) LLM models in OARS. We will invite experts and papers in the field to disseminate new knowledge and foster further advancements.

Recommender system (RecSys) plays important roles in helping users navigate, discover, and consume massive and highly-dynamic information. Today, many RecSys solutions deployed in the real world rely on categorical user-profiles and/or pre-calculated recommendation actions that stay static during a user session. However, recent trends suggest that RecSys need to model user intent in real time and constantly adapt to meet user needs at the moment or change user behavior in situ. There are three primary drivers for this emerging need of online adaptation. First, in order to meet the increasing demand for a better personalized experience, the personalization dimensions and space will grow larger and larger. It would not be feasible to pre-compute recommended actions for all personalization scenarios beyond a certain scale. Second, in many settings the system does not have user prior history to leverage. Estimating user intent in real time is the only feasible way to personalize. As various consumer privacy laws tighten, it is foreseeable that many businesses will reduce their reliance on static user profiles. Therefore, it makes the modeling of user intent in real time an important research topic. Third, a user's intent often changes within a session and between sessions, and user behavior could shift significantly during dramatic events. Therefore, it is important to investigate more on online and adaptive recommender system (OARS) that can adapt in real time to meet user needs and be robust against distribution shifts. Every year, the organizers survey the most important topics for OARS and propose a new workshop program. In light of the recent advancement of LLMs and foundation models in RecSys, in this new edition, we decide to formally add the new topic of foundation and LLM models in OARS. We will invite experts and papers in the field to facilitate its further advancement. Our workshop offers a focused discussion of the new study and application of OARS, and will bring together an interdisciplinary community of researchers and practitioners from both industry and academia to discuss on new topics in the area, grow a community, and push the direction forward.

Over the past few years, consumer behavior has shifted from traditional in-store shopping to online shopping. For example, eCommerce sales have grown from around 5% of total US sales in 2012 to around 15.4% in year 2023. This rapid growth of eCommerce has created new challenges and vital new requirements for intelligent information retrieval systems. Which lead to the primary motivations of this workshop:

Recommender systems (RecSys) play important roles in helping users navigate, discover, and consume large and highly dynamic information. Today, many RecSys solutions deployed in the real world rely on categorical user-profiles and/or pre-calculated recommendation actions that stay static during a user session. However, recent trends suggest that RecSys need to model user intent in real time and constantly adapt to meet user needs at the moment or change user behavior in situ. There are three primary drivers for this emerging need of online adaptation. First, in order to meet the increasing demand for a better personalized experience, the personalization dimensions and space will grow larger and larger. It would not be feasible to pre-compute recommended actions for all personalization scenarios beyond a certain scale. Second, in many settings the system does not have user prior history to leverage. Estimating user intent in real time is the only feasible way to personalize. As various consumer privacy laws tighten, it is foreseeable that many businesses will reduce their reliance on static user profiles. Therefore, it makes the modeling of user intent in real time an important research topic. Third, a user's intent often changes within a session and between sessions, and user behavior could shift significantly during dramatic events. A RecSys should adapt in real time to meet user needs and be robust against distribution shifts. The online and adaptive recommender systems (OARS) workshop offers a focused discussion of the study and application of OARS, and will bring together an interdisciplinary community of researchers and practitioners from both industry and academia. KDD, as the premier data science conference, is an ideal venue to gather leaders in the field to further research into OARS and promote its adoption. This workshop is complementary to several sessions of the main conference (e.g., recommendation, reinforcement learning, etc.) and brings them together using a practical and focused application.

Query Understanding (QU) is a fundamental process in E-commerce search engines by extracting the shopping intents of customers. It usually includes a set of different tasks such as named entity recognization and query classification. Traditional approaches often tackle each task separately by its own network, which leads to excessive workload for development and maintenance as well as increased latency and resource usage in large-scale E-commerce platforms. To tackle these challenges, this paper presents a multi-task learning approach to query understanding at Walmart. We experimented with several state-of-the-art multi-task learning architectures including MTDNN, MMoE, and PLE. Furthermore, we propose a novel large-scale entity-aware multi-task learning model (EAMT)1 by retrieving entities from engagement data as query context to augment the query representation. To the best of our knowledge, there exists no prior work on multi-task learning for E-commerce query understanding. Comprehensive offline experiments are conducted on industry-scale datasets (up to 965M queries) to illustrate the effectiveness of our approach. The results from online experiments show substantial gains in key accuracy and latency metrics. https://github.com/zhiyuanpeng/KDD2023-EAMT

Recommender systems (RecSys) play important roles in helping users navigate, discover, and consume large and highly dynamic information. Today, many RecSys solutions deployed in the real world rely on categorical user-profiles and/or pre-calculated recommendation actions that stay static during a user session. However, recent trends suggest that RecSys need to model user intent in real time and constantly adapt to meet user needs at the moment or change user behavior in situ. There are three primary drivers for this emerging need of online adaptation. First, in order to meet the increasing demand for a better personalized experience, the personalization dimensions and space will grow larger and larger. It would not be feasible to pre-compute recommended actions for all personalization scenarios beyond a certain scale. Second, in many settings the system does not have user prior history to leverage. Estimating user intent in real time is the only feasible way to personalize. As various consumer privacy laws tighten, it is foreseeable that many businesses will reduce their reliance on static user profiles. Therefore, it makes the modeling of user intent in real time an important research topic. Third, a user's intent often changes within a session and between sessions, and user behavior could shift significantly during dramatic events. A RecSys should adapt in real time to meet user needs and be robust against distribution shifts. The online and adaptive recommender systems (OARS) workshop offers a focused discussion of the study and application of OARS, and will bring together an interdisciplinary community of researchers and practitioners from both industry and academia. KDD, as the premier data science conference, is an ideal venue to gather leaders in the field to further research into OARS and promote its adoption. This workshop is complementary to several sessions of the main conference (e.g., recommendation, reinforcement learning, etc.) and brings them together using a practical and focused application.

Many recommender systems deployed in the real world rely on categorical user-profiles and/or pre-calculated recommendation actions that stay static during a user session. Recent trends suggest that recommender systems should model user intent in real time and constantly adapt to meet user needs at the moment or change user behavior in situ. In addition, there have been many advances that make online and adaptive recommender systems (OARS) feasible, scalable, and more sophisticated. This workshop aims to bring together practitioners and researchers from academia and industry to discuss the challenges and approaches to implement OARS algorithms and systems and improve user experiences by better modeling and responding to user intent.

Network embedding methodologies, which learn a distributed vector representation for each vertex in a network, have shown to achieve superior performance in many real-world applications, such as node classification, link prediction, and community detection. However, the existing methods for network embedding are unable to generate representation vectors for unseen vertices; besides, these methods only utilize topological information from the network ignoring a rich set of nodal attributes, which is abundant in all real-life networks. In this paper, we present a novel network embedding approach called Neural-Brane, which overcomes both of the above limitations. For a given network, Neural-Brane extracts latent feature representation of its vertices using a designed neural network model that unifies network topological information and nodal attributes. Additionally, Neural-Brane is an inductive embedding approach, which enables generating embedding vectors for unseen future vertices of the attributed network. We evaluate the quality of vertex embedding produced by Neural-Brane by solving the node classification task on four real-world graph datasets. Experimental results demonstrate the superiority of Neural-Brane over the state-of-the-art existing methods.

Network embedding methodologies, which learn a distributed vector representation for each vertex in a network, have attracted considerable interest in recent years. Existing works have demonstrated that vertex representation learned through an embedding method provides superior performance in many real-world applications, such as node classification, link prediction, and community detection. However, most of the existing methods for network embedding only utilize topological information of a vertex, ignoring a rich set of nodal attributes (such as user profiles of an online social network, or textual contents of a citation network), which is abundant in all real-life networks. A joint network embedding that takes into account both attributional and relational information entails a complete network information and could further enrich the learned vector representations. In this work, we present Neural-Brane , a novel Neural B ayesian Personalized R anking based A ttributed N etwork E mbedding. For a given network, Neural-Brane extracts latent feature representation of its vertices using a designed neural network model that unifies network topological information and nodal attributes. Besides, it utilizes Bayesian personalized ranking objective, which exploits the proximity ordering between a similar node pair and a dissimilar node pair. We evaluate the quality of vertex embedding produced by Neural-Brane by solving the node classification and clustering tasks on four real-world datasets. Experimental results demonstrate the superiority of our proposed method over the state-of-the-art existing methods.

Job recommendation is an important task for the modern recruitment industry. An excellent job recommender system not only enables to recommend a higher paying job which is maximally aligned with the skill-set of the current job, but also suggests to acquire few additional skills which are required to assume the new position. In this work, we created three types of information net- works from the historical job data: (i) job transition network, (ii) job-skill network, and (iii) skill co-occurrence network. We provide a representation learning model which can utilize the information from all three networks to jointly learn the representation of the jobs and skills in the shared k-dimensional latent space. In our experiments, we show that by jointly learning the representation for the jobs and skills, our model provides better recommendation for both jobs and skills. Additionally, we also show some case studies which validate our claims.

In recent years, graphlet counting has emerged as an important task in topological graph analysis. However, the existing works on graphlet counting obtain the graphlet counts for the entire network as a whole. These works capture the key graphical patterns that prevail in a given network but they fail to meet the demand of the majority of real-life graph related prediction tasks such as link prediction, edge/node classification, etc., which require to build features for an edge (or a vertex) of a network. To meet the demand for such applications, efficient algorithms are needed for counting local graphlets within the context of an edge (or a vertex). In this work, we propose an efficient method, titled E-CLOG, for counting all 3,4 and 5 size local graphlets with the context of a given edge for its all different edge orbits. We also provide a shared-memory, multi-core implementation of E-CLOG, which makes it even more scalable for very large real-world networks. In particular, We obtain strong scaling on a variety of graphs (14x-20x on 36 cores). We provide extensive experimental results to demonstrate the efficiency and effectiveness of the proposed method. For instance, we show that E-CLOG is faster than existing work by multiple order of magnitudes; for the Wordnet graph E-CLOG counts all 3,4 and 5-size local graphlets in 1.5 hours using a single thread and in only a few minutes using the parallel implementation, whereas the baseline method does not finish in more than 4 days. We also show that local graphlet counts around an edge are much better features for link prediction than well-known topological features; our experiments show that the former enjoys between 10% to 45% of improvement in the AUC value for predicting future links in three real-life social and collaboration networks.

In the recruitment domain, the employer name normalization task, which links employer names in job postings or resumes to entities in an employer knowledge base (KB), is important to many business applications. In previous work, we proposed the CompanyDepot system, which used machine learning techniques to address the problem. After applying it to several applications at CareerBuilder, we faced several new challenges: 1) how to avoid duplicate normalization results when the KB is noisy and contains many duplicate entities; 2) how to address the vocabulary gap between query names and entity names in the KB; and 3) how to use the context available in jobs and resumes to improve normalization quality.