Related papers: Learning Compact Compositional Embeddings via Regu…

Unsupervised feature learning often finds low-dimensional embeddings that capture the structure of complex data. For tasks for which prior expert topological knowledge is available, incorporating this into the learned representation may…

Recurrent neural networks (RNNs) have achieved state-of-the-art performances in many natural language processing tasks, such as language modeling and machine translation. However, when the vocabulary is large, the RNN model will become very…

State-of-the-art recommender system (RS) mostly rely on complex deep neural network (DNN) model structure, which makes it difficult to provide explanations along with RS decisions. Previous researchers have proved that providing…

Deep learning for recommendation data is one of the most pervasive and challenging AI workload in recent times. State-of-the-art recommendation models are one of the largest models matching the likes of GPT-3 and Switch Transformer.…

On-device session-based recommendation systems have been achieving increasing attention on account of the low energy/resource consumption and privacy protection while providing promising recommendation performance. To fit the powerful…

Language representation learning has emerged as a promising approach for sequential recommendation, thanks to its ability to learn generalizable representations. However, despite its advantages, this approach still struggles with data…

Due to the development of graph neural networks, graph-based representation learning methods have made great progress in recommender systems. However, data sparsity is still a challenging problem that most graph-based recommendation methods…

Deep learning models achieve strong performance across various domains but often rely on spurious correlations, making them vulnerable to distribution shifts. This issue is particularly severe in subpopulation shift scenarios, where models…

Assembly-based tools provide a powerful modeling paradigm for non-expert shape designers. However, choosing a component from a large shape repository and aligning it to a partial assembly can become a daunting task. In this paper we…

Multi-criteria recommender systems have been increasingly valuable for helping consumers identify the most relevant items based on different dimensions of user experiences. However, previously proposed multi-criteria models did not take…

Following recent successes in exploiting both latent factor and word embedding models in recommendation, we propose a novel Regularized Multi-Embedding (RME) based recommendation model that simultaneously encapsulates the following ideas…

Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve strong quality through fine-grained token-level matching but…

Learned Sparse Retrieval (LSR) such as SPLADE has growing interest for effective semantic 1st stage matching while enjoying the efficiency of inverted indices. A recent work on learning SPLADE models with expanded vocabularies (ESPLADE) was…

Feature embeddings are one of the most essential steps when training deep learning based Click-Through Rate prediction models, which map high-dimensional sparse features to dense embedding vectors. Classic human-crafted embedding size…

Conversational recommender systems (CRS) aim to recommend suitable items to users through natural language conversations. For developing effective CRSs, a major technical issue is how to accurately infer user preference from very limited…

Convolutional Neural Networks (CNNs) pre-trained on large-scale datasets such as ImageNet are widely used as feature extractors to construct high-accuracy classification models from scarce data for specific tasks. In such scenarios,…

Text embedding models play a crucial role in natural language processing, particularly in information retrieval, and their importance is further highlighted with the recent utilization of RAG (Retrieval- Augmented Generation). This study…

Learning a good representation of text is key to many recommendation applications. Examples include news recommendation where texts to be recommended are constantly published everyday. However, most existing recommendation techniques, such…

As deep neural networks are growing in size and being increasingly deployed to more resource-limited devices, there has been a recent surge of interest in network pruning methods, which aim to remove less important weights or activations of…

Deep learning has brought significant breakthroughs in sequential recommendation (SR) for capturing dynamic user interests. A series of recent research revealed that models with more parameters usually achieve optimal performance for SR…