Related papers: Joint Model Parameter Scaling and Universal-Domain…

Automated Machine Learning (AutoML) techniques have recently been introduced to design Collaborative Filtering (CF) models in a data-specific manner. However, existing works either search architectures or hyperparameters while ignoring the…

The industrial recommender systems always pursue more than one business goals. The inherent intensions between objectives pose significant challenges for ranking stage. A popular solution is to build a multi-objective ensemble (ME) model to…

In recommendation systems, the traditional multi-stage paradigm, which includes retrieval and ranking, often suffers from information loss between stages and diminishes performance. Recent advances in generative models, inspired by natural…

While scaling laws promise significant performance gains for recommender systems, efficiently deploying hyperscale models remains a major unsolved challenge. In contrast to fields where FMs are already widely adopted such as natural…

Federated Semi-Supervised Learning (FSSL) aims to learn a global model from different clients in an environment with both labeled and unlabeled data. Most of the existing FSSL work generally assumes that both types of data are available on…

Large language models (LLMs) exhibit varying strengths and weaknesses across different tasks, prompting recent studies to explore the benefits of ensembling models to leverage their complementary advantages. However, existing LLM ensembling…

Modern computational advertising platforms typically rely on recommendation systems to predict user responses, such as click-through rates, conversion rates, and other optimization events. To support a wide variety of product surfaces and…

In this work, we propose a Unified framework of Sequential Search and Recommendation (UnifiedSSR) for joint learning of user behavior history in both search and recommendation scenarios. Specifically, we consider user-interacted products in…

Existing benchmarks for summarization quality evaluation often lack diverse input scenarios, focus on narrowly defined dimensions (e.g., faithfulness), and struggle with subjective and coarse-grained annotation schemes. To address these…

Recently, community has paid increasing attention on model scaling and contributed to developing a model family with a wide spectrum of scales. Current methods either simply resort to a one-shot NAS manner to construct a non-structural and…

Modeling user preferences has been mainly addressed by looking at users' interaction history with the different elements available in the system. Tailoring content to individual preferences based on historical data is the main goal of…

Model-based clustering integrated with variable selection is a powerful tool for uncovering latent structures within complex data. However, its effectiveness is often hindered by challenges such as identifying relevant variables that define…

As neural networks continue to grow in size but datasets might not, it is vital to understand how much performance improvement can be expected: is it more important to scale network size or data volume? Thus, neural network scaling laws,…

Searching and detecting communities in real-world graphs underpins a wide range of applications. Despite the success achieved, current learning-based solutions regard community search, i.e., locating the best community for a given query,…

The design of structural & functional materials for specialized applications is being fueled by rapid advancements in materials synthesis, characterization, manufacturing, with sophisticated computational materials modeling frameworks that…

Model merging efficiently aggregates capabilities from multiple fine-tuned models into a single one, operating purely in parameter space without original data or expensive re-computation. Despite empirical successes, a unified theory for…

Dimensional data reduction methods are fundamental to explore and visualize large data sets. Basic requirements for unsupervised data exploration are simplicity, flexibility and scalability. However, current methods show complex…

With the prosperity of e-commerce industry, various modalities, e.g., vision and language, are utilized to describe product items. It is an enormous challenge to understand such diversified data, especially via extracting the…

Automating the design of heuristic search methods is an active research field within computer science, artificial intelligence and operational research. In order to make these methods more generally applicable, it is important to eliminate…

Inspired by the success of language models (LM), scaling up deep learning recommendation systems (DLRS) has become a recent trend in the community. All previous methods tend to scale up the model parameters during training time. However,…