Related papers: GateSID: Adaptive Gating for Semantic-Collaborativ…

Sequential recommender systems rank relevant items by modeling a user's interaction history and computing the inner product between the resulting user representation and stored item embeddings. To avoid the significant memory overhead of…

By taking the idea of divide-and-conquer, cooperative coevolution (CC) provides a powerful architecture for large scale global optimization (LSGO) problems, but its efficiency relies highly on the decomposition strategy. It has been shown…

In modern e-commerce, item content features in various modalities offer accurate yet comprehensive information to recommender systems. The majority of previous work either focuses on learning effective item representation during modelling…

With the rapid growth of digital information, personalized recommendation systems have become an indispensable part of Internet services, especially in the fields of e-commerce, social media, and online entertainment. However, traditional…

The recent popularity of edge devices and Artificial Intelligent of Things (AIoT) has driven a new wave of contextual recommendations, such as location based Point of Interest (PoI) recommendations and computing resource-aware mobile app…

Graph transformers achieve strong results on molecular and long-range reasoning tasks, yet remain hampered by over-smoothing (the progressive collapse of node representations with depth) and attention entropy degeneration. We observe that…

Cloth-changing person reidentification (ReID) is a newly emerging research topic that aims to retrieve pedestrians whose clothes are changed. Since the human appearance with different clothes exhibits large variations, it is very difficult…

This study introduces a pioneering methodology for human action recognition by harnessing deep neural network techniques and adaptive fusion strategies across multiple modalities, including RGB, optical flows, audio, and depth information.…

Recommendation systems suffer in the strict cold-start (SCS) scenario, where the user-item interactions are entirely unavailable. The ID-based approaches completely fail to work. Cold-start recommenders, on the other hand, leverage item…

Multimodal learning integrates diverse modalities but suffers from modality imbalance, where dominant modalities suppress weaker ones due to inconsistent convergence rates. Existing methods predominantly rely on static modulation or…

Stochastic gradient descent (SGD) has taken the stage as the primary workhorse for large-scale machine learning. It is often used with its adaptive variants such as AdaGrad, Adam, and AMSGrad. This paper proposes an adaptive stochastic…

Collaborative filtering tries to predict the ratings of a user over some items based on opinions of other users with similar taste. The ratings are usually given in the form of a sparse matrix, the goal being to find the missing entries…

Synchronous federated learning scales poorly due to the straggler effect. Asynchronous algorithms increase the update throughput by processing updates upon arrival, but they introduce two fundamental challenges: gradient staleness, which…

Conversational news recommendation requires grounding each suggestion in a rapidly evolving article corpus while addressing implicit user intents that lack explicit retrievable keywords. To characterize this scenario, we identify 6 intent…

Generative models powered by Large Language Models (LLMs) are emerging as a unified solution for powering both recommendation and search tasks. A key design choice in these models is how to represent items, traditionally through unique…

As the AI community increasingly adopts large-scale models, it is crucial to develop general and flexible tools to integrate them. We introduce Gather-Attend-Scatter (GATS), a novel module that enables seamless combination of pretrained…

Few-Shot Industrial Visual Anomaly Detection (FS-IVAD) comprises a critical task in modern manufacturing settings, where automated product inspection systems need to identify rare defects using only a handful of normal/defect-free training…

Multimodal recommendation enhances ranking by integrating user-item interactions with item content, which is particularly effective under sparse feedback and long-tail distributions. However, multimodal signals are inherently heterogeneous…

Sparse Autoencoders (SAEs) extract interpretable features from Large Language Models, but standard variants enforce non-negativity, forcing separate latents for diametrically opposed concepts (e.g., "pressure too high" vs. "pressure too…

In text-to-image personalization, a timely and crucial challenge is the tendency of generated images overfitting to the biases present in the reference images. We initiate our study with a comprehensive categorization of the biases into…