paper-with-me

Papers

Scaling Experiments in Self-Supervised Cross-Table Representation Learning

2023-09-29 · Maximilian Schambach, Dominique Paul, Johannes S. Otterbach

To analyze the scaling potential of deep tabular representation learning models, we introduce a novel Transformer-based architecture specifically tailored to tabular data and cross-table representation learning by utilizing table-specific tokenizers and a shared Transformer backbone. Our training approach encompasses both single-table and cross-table models, trained via missing value imputation through a self-supervised masked cell recovery objective. To understand the scaling behavior of our method, we train models of varying sizes, ranging from approximately $10^4$ to $10^7$ parameters. These models are trained on a carefully curated pretraining dataset, consisting of 135M training tokens sourced from 76 diverse datasets. We assess the scaling of our architecture in both single-table and cross-table pretraining setups by evaluating the pretrained models using linear probing on a curated set of benchmark datasets and comparing the results with conventional baselines.

📄 PDF Abstract BibTeX arXiv:2309.17339

Code (0)

등록된 구현이 없습니다.

Tasks

ImputationRepresentation Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video

2026-05-29 · Ulrich Prestel, Stefan Andreas Baumann, Nick Stracke, Björn Ommer arxiv

Self-supervised novel view synthesis (NVS) remains challenging to scale, despite the abundance of video data, largely due to the brittleness of training on realistic videos and the hard-to-predict scaling behavior of mul…

Novel View Synthesis

On Model and Data Scaling for Skeleton-based Self-Supervised Gait Recognition

2025-04-10 · Adrian Cosma, Andy Cǎtrunǎ, Emilian Rǎdoi

Gait recognition from video streams is a challenging problem in computer vision biometrics due to the subtle differences between gaits and numerous confounding factors. Recent advancements in self-supervised pretraining …

Gait Recognition

Scaling and Benchmarking Self-Supervised Visual Representation Learning

2019-05-03 · ICCV 2019 10 · Priya Goyal, Dhruv Mahajan, Abhinav Gupta, Ishan Misra

Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning - the ability to scale to large amount…

Benchmarkingobject-detectionObject DetectionReinforcement Learning+4

CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulators

2026-05-09 · Nicolás Astorga, Anita Kriz, Mihaela van der Schaar arxiv

Despite surpassing human performance across mathematics, coding, and other knowledge-intensive tasks, large language models (LLMs) continue to struggle with causal reasoning. A core obstacle is the target data itself: ca…

Data Augmentation

Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformers

2025-11-21 · Cris Claessens, Christiaan Viviers, Giacomo D'Amicantonio, Egor Bondarev 외 arxiv

We introduce SPECTRE, a fully transformer-based foundation model for volumetric computed tomography (CT). Our Self-Supervised & Cross-Modal Pretraining for CT Representation Extraction (SPECTRE) approach utilizes scalabl…

Contrastive Learning