Related papers: Representation for alphanumeric data type based on…

Text-to-SQL enables non-experts to retrieve data from databases by converting natural language queries into SQL. However, state-of-the-art text-to-SQL studies rely on the BIRD dataset, which assumes that evidence is provided along with…

How data is represented and operationalized is critical for building computational solutions that are both effective and efficient. A common approach is to represent data objects as binary vectors, denoted \textit{hash codes}, which require…

Large-scale short-video search ranking models are typically trained on sparse co-occurrence signals over hashed item identifiers (HIDs). While effective at memorizing frequent interactions, such ID-based models struggle to generalize to…

The concept of dimension is essential to grasp the complexity of data. A naive approach to determine the dimension of a dataset is based on the number of attributes. More sophisticated methods derive a notion of intrinsic dimension (ID)…

Computer representations of real numbers are necessarily discrete, with some finite resolution, discreteness, quantization, or minimum representable difference. We perform astrometric and photometric measurements on stars and co-add…

Knowledge distillation is widely adopted in semantic segmentation to reduce the computation cost.The previous knowledge distillation methods for semantic segmentation focus on pixel-wise feature alignment and intra-class feature variation…

We study the problem of constructing a dynamic fully indexable dictionary (FID) in the Word-RAM model using space close to the information-theoretic lower bound. A FID is a data-structure that encodes a bit-vector $B$ of length $u$ and…

Generative retrieval, a promising new paradigm in information retrieval, employs a seq2seq model to encode document features into parameters and decode relevant document identifiers (IDs) based on search queries. Existing generative…

Semantic ID learning is a key interface in Generative Recommendation (GR) models, mapping items to discrete identifiers grounded in side information, most commonly via a pretrained text encoder. However, these text encoders are primarily…

Data drift is a thorny challenge when deploying person re-identification (ReID) models into real-world devices, where the data distribution is significantly different from that of the training environment and keeps changing. To tackle this…

Among the entities involved in software citation, software source code requires special attention, due to the role it plays in ensuring scientific reproducibility. To reference source code we need identifiers that are not only unique and…

Fraud (swindling money, property, or authority by fictionizing, counterfeiting, forging, or imitating things, or by feigning other persons privately) forms its threats against public security and network security. Anti-fraud is essentially…

For many use-cases, it is often important to explain the prediction of a black-box model by identifying the most influential training data samples. Existing approaches lack customization for user intent and often provide a homogeneous set…

Language Identification (LID) systems are used to classify the spoken language from a given audio sample and are typically the first step for many spoken language processing tasks, such as Automatic Speech Recognition (ASR) systems. Without…

Measures of similarity (or dissimilarity) are a key ingredient to many machine learning algorithms. We introduce DID, a pairwise dissimilarity measure applicable to a wide range of data spaces, which leverages the data's internal structure…

Semantic IDs (SIDs) are compact discrete representations derived from multimodal item features, serving as a unified abstraction for ID-based and generative recommendation. However, learning high-quality SIDs remains challenging due to two…

We consider the problem of information-theoretic secrecy in identification schemes rather than transmission schemes. In identification, large identities are encoded into small challenges sent with the sole goal of allowing at the receiver…

The Partial Information Decomposition (PID) takes one step beyond Shannon's theory in decomposing the information two variables $A,B$ possess about a third variable $T$ into distinct parts: unique, shared (or redundant) and synergistic…

Imbalance in classification tasks is commonly quantified by the cardinalities of examples across classes. This, however, disregards the presence of redundant examples and inherent differences in the learning difficulties of classes.…

Edge intelligence requires to fast access distributed data samples generated by edge devices. The challenge is using limited radio resource to acquire massive data samples for training machine learning models at edge server. In this…