相关论文: ET-BERT: A Contextualized Datagram Representation …

Existing cross-encoder models can be categorized as pointwise, pairwise, or listwise. Pairwise and listwise models allow passage interactions, which typically makes them more effective than pointwise models but less efficient and less…

The widespread adoption of encrypted communication protocols such as HTTPS and TLS has enhanced data privacy but also rendered traditional anomaly detection techniques less effective, as they often rely on inspecting unencrypted payloads.…

This paper investigates fake news detection as a downstream evaluation of Transformer representations, benchmarking encoder-only and decoder-only pre-trained models (BERT, GPT-2, Transformer-XL) as frozen embedders paired with lightweight…

This paper presents a novel approach to accurately classify the hallmarks of cancer, which is a crucial task in cancer research. Our proposed method utilizes the Bidirectional Encoder Representations from Transformers (BERT) architecture,…

In this paper, we propose a privacy-preserving image classification method that uses encrypted images and an isotropic network such as the vision transformer. The proposed method allows us not only to apply images without visual information…

We present iBERT (interpretable-BERT), an encoder to produce inherently interpretable and controllable embeddings - designed to modularize and expose the discriminative cues present in language, such as semantic or stylistic structure. Each…

Recently, Transformers for graph representation learning have become increasingly popular, achieving state-of-the-art performance on a wide-variety of graph datasets, either alone or in combination with message-passing graph neural networks…

Representation learning in recent years has been addressed with self-supervised learning methods. The input data is augmented into two distorted views and an encoder learns the representations that are invariant to distortions -- cross-view…

One critical component in lossy deep image compression is the entropy model, which predicts the probability distribution of the quantized latent representation in the encoding and decoding modules. Previous works build entropy models upon…

Understanding the traffic dynamics in networks is a core capability for automated systems to monitor and analyze networking behaviors, reducing expensive human efforts and economic risks through tasks such as traffic classification,…

Multi-graph learning is crucial for extracting meaningful signals from collections of heterogeneous graphs. However, effectively integrating information across graphs with differing topologies, scales, and semantics, often in the absence of…

In meta-learning approaches, it is difficult for a practitioner to make sense of what kind of representations the model employs. Without this ability, it can be difficult to both understand what the model knows as well as to make meaningful…

Graph neural network-based network intrusion detection systems have recently demonstrated state-of-the-art performance on benchmark datasets. Nevertheless, these methods suffer from a reliance on target encoding for data pre-processing,…

The digitization of traffic sensing infrastructure has significantly accumulated an extensive traffic data warehouse, which presents unprecedented challenges for transportation analytics. The complexities associated with querying…

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Transformer models are permutation equivariant. To supply the order and type information of the input tokens, position and segment embeddings are usually added to the input. Recent works proposed variations of positional encodings with…

Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech…

Unsupervised sentence representation learning aims to transform input sentences into fixed-length vectors enriched with intricate semantic information while obviating the reliance on labeled data. Recent strides within this domain have been…

Pretraining plays a pivotal role in acquiring generalized knowledge from large-scale data, achieving remarkable successes as evidenced by large models in CV and NLP. However, progress in the graph domain remains limited due to fundamental…

Recently, a variety of acoustic tasks and related applications arised. For many acoustic tasks, the labeled data size may be limited. To handle this problem, we propose an unsupervised pre-training method using Transformer based encoder to…