Related papers: A Plug-and-play Model-agnostic Embedding Enhanceme…

To improve word representation learning, we propose a probabilistic prior which can be seamlessly integrated with word embedding models. Different from previous methods, word embedding is taken as a probabilistic generative model, and it…

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

Recent breakthroughs in large language models (LLMs) have fundamentally shifted recommender systems from discriminative to generative paradigms, where user behavior modeling is achieved by generating target items conditioned on historical…

Most of existing embedding based recommendation models use embeddings (vectors) corresponding to a single fixed point in low-dimensional space, to represent users and items. Such embeddings fail to precisely represent the users/items with…

Selective prediction aims to endow predictors with a reject option, to avoid low confidence predictions. However, existing literature has primarily focused on closed-set tasks, such as visual question answering with predefined options or…

User embeddings (vectorized representations of a user) are essential in recommendation systems. Numerous approaches have been proposed to construct a representation for the user in order to find similar items for retrieval tasks, and they…

Recent advancements of sequential deep learning models such as Transformer and BERT have significantly facilitated the sequential recommendation. However, according to our study, the distribution of item embeddings generated by these models…

Embedding-based retrieval (EBR) methods are widely used in modern recommender systems thanks to its simplicity and effectiveness. However, along the journey of deploying and iterating on EBR in production, we still identify some fundamental…

Network representation learning (NRL) methods aim to map each vertex into a low dimensional space by preserving the local and global structure of a given network, and in recent years they have received a significant attention thanks to…

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…

Information technology has spread widely, and extraordinarily large amounts of data have been made accessible to users, which has made it challenging to select data that are in accordance with user needs. For the resolution of the above…

Multi-interest learning method for sequential recommendation aims to predict the next item according to user multi-faceted interests given the user historical interactions. Existing methods mainly consist of a multi-interest extractor that…

Rapid advances in GPU hardware and multiple areas of Deep Learning open up a new opportunity for billion-scale information retrieval with exhaustive search. Building on top of the powerful concept of semantic learning, this paper proposes a…

Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or…

In today's context, deploying data-driven services like recommendation on edge devices instead of cloud servers becomes increasingly attractive due to privacy and network latency concerns. A common practice in building compact on-device…

Recent methods for reinforcement learning from images use auxiliary tasks to learn image features that are used by the agent's policy or Q-function. In particular, methods based on contrastive learning that induce linearity of the latent…

Neural Collaborative Filtering models are widely used in recommender systems but are typically trained under static settings, assuming fixed data distributions. This limits their applicability in dynamic environments where user preferences…

Music retrieval and recommendation applications often rely on content features encoded as embeddings, which provide vector representations of items in a music dataset. Numerous complementary embeddings can be derived from processing items…

Despite recent monumental advances in the field, many Natural Language Processing (NLP) models still struggle to perform adequately on noisy domains. We propose a novel probabilistic embedding-level method to improve the robustness of NLP…

In this work, we propose an acoustic embedding based approach for representation learning in speech recognition. The proposed approach involves two stages comprising of acoustic filterbank learning from raw waveform, followed by modulation…