相关论文: Learning Backward Compatible Embeddings

Click-through rate (CTR) prediction has been one of the most central problems in computational advertising. Lately, embedding techniques that produce low-dimensional representations of ad IDs drastically improve CTR prediction accuracies.…

Concept Bottleneck Models (CBMs) aim to enhance interpretability by predicting human-understandable concepts as intermediates for decision-making. However, these models often face challenges in ensuring reliable concept representations,…

We introduce a self-supervised representation learning method based on the task of temporal alignment between videos. The method trains a network using temporal cycle consistency (TCC), a differentiable cycle-consistency loss that can be…

Concept bottleneck models (CBMs) have emerged as critical tools in domains where interpretability is paramount. These models rely on predefined textual descriptions, referred to as concepts, to inform their decision-making process and offer…

Multimodal learning plays a critical role in e-commerce recommendation platforms today, enabling accurate recommendations and product understanding. However, existing vision-language models, such as CLIP, face key challenges in e-commerce…

Product recommendation is the task of recovering the closest items to a given query within a large product corpora. Generally, one can determine if top-ranked products are related to the query by applying a similarity threshold; exceeding…

Function association is a useful process for binary reverse engineers. Search tools exist to perform association at scale, but they do not utilize the full range of capabilities that AI-enabled search provides. Prior work has explored the…

Recommendation algorithms that incorporate techniques from deep learning are becoming increasingly popular. Due to the structure of the data coming from recommendation domains (i.e., one-hot-encoded vectors of item preferences), these…

Contrastive learning operates on a simple yet effective principle: Embeddings of positive pairs are pulled together, while those of negative pairs are pushed apart. In this paper, we propose a unified framework for understanding contrastive…

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Recommending appropriate algorithms to a classification problem is one of the most challenging issues in the field of data mining. The existing algorithm recommendation models are generally constructed on only one kind of meta-features by…

Recommender systems typically represent users and items by learning their embeddings, which are usually set to uniform dimensions and dominate the model parameters. However, real-world recommender systems often operate in streaming…

We propose a novel multi-dimensional integration algorithm using a machine learning (ML) technique. After training a ML regression model to mimic a target integrand, the regression model is used to evaluate an approximation of the integral.…

Recent advancements in machine learning (ML), natural language processing (NLP), and foundational models have shown promise for real-life applications in critical, albeit compute-constrainted fields like healthcare. In such areas, combining…

Online misinformation remains a critical challenge, and fact-checkers increasingly rely on claim matching systems that use sentence embedding models to retrieve relevant fact-checks. However, as users interact with claims online, they often…

Embedding fusion has emerged as an effective approach for enhancing performance across various NLP tasks. However, systematic guidelines for selecting optimal layers and developing effective fusion strategies for the integration of LLMs…

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…

Feature selection removes redundant features to enhanc performance and computational efficiency in downstream tasks. Existing works often struggle to capture complex feature interactions and adapt to diverse scenarios. Recent advances in…

Backdoor attacks allow an attacker to embed a specific vulnerability in a machine learning algorithm, activated when an attacker-chosen pattern is presented, causing a specific misprediction. The need to identify backdoors in biometric…

Providing model-generated explanations in recommender systems is important to user experience. State-of-the-art recommendation algorithms - especially collaborative filtering (CF)-based approaches with shallow or deep models - usually work…