paper-with-me

홈 › Papers

Deep Representational Re-tuning using Contrastive Tension

2021-01-01 · ICLR 2021 1 · Fredrik Carlsson, Amaru Cuba Gyllensten, Evangelia Gogoulou, Erik Ylipää Hellqvist, Magnus Sahlgren

Extracting semantically useful natural language sentence representations from pre-trained deep neural networks such as Transformers remains a challenge. We first demonstrate that pre-training objectives impose a significant task bias onto the final layers of models with a layer-wise survey of the Semantic Textual Similarity (STS) correlations for multiple common Transformer language models. We then propose a new self-supervised method called Contrastive Tension (CT) to counter such biases. CT frames the training objective as a noise-contrastive task between the final layer representations of two independent models, in turn making the final layer representations suitable for feature extraction. Results from multiple common unsupervised and supervised STS tasks indicate that CT outperforms previous State Of The Art (SOTA), and when combining CT with supervised data we improve upon previous SOTA results with large margins.

📄 PDF Abstract BibTeX

Code (1)

FreddeFrallan/Contrastive-Tension 공식 구현 tf

Tasks

Semantic SimilaritySemantic Textual SimilaritySentenceSentence EmbeddingSentence EmbeddingsSTS

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Multi-Head Attention 설명 없음
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…

Similar Papers 제목 키워드 기반

CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning

2025-03-25 · Hao Yu, Zhuokai Zhao, Shen Yan, Lukasz Korycki 외

The rapid advancement of large vision-language models (LVLMs) has driven significant progress in multimodal tasks, enabling models to interpret, reason, and generate outputs across both visual and textual domains. While …

HallucinationLanguage ModelingLanguage ModellingObject Hallucination+2

Counterfactual Basis Extension and Representational Geometry: An MDL-Constrained Model of Conceptual Growth

2025-12-21 · Chainarong Amornbunchornvej arxiv

Concept learning becomes possible only when existing representations fail to account for experience. Most models of learning and inference, however, presuppose a fixed representational basis within which belief updating …

Do Foundation Models Know Geometry? Probing Frozen Features for Continuous Physical Measurement

2026-03-06 · Yakov Pyotr Shkolnikov arxiv

Vision-language models encode continuous geometry that their text pathway fails to express: a 6,000-parameter linear probe extracts hand joint angles at 6.1 degrees MAE from frozen features, while the best text output ac…

Text Generation

It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap

2024-05-28 · Abrar Fahim, Alex Murphy, Alona Fyshe

Multi-modal contrastive models such as CLIP achieve state-of-the-art performance in zero-shot classification by embedding input images and texts on a joint representational space. Recently, a modality gap has been report…

image-classificationImage Classificationzero-shot-classificationZero-Shot Image Classification+1

Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts

2026-05-20 · Gene Tangtartharakul, Katherine R. Storrs arxiv

Mixture-of-Experts (MoE) models are often interpreted by analysing which categories are routed to which experts. However, routing alone does not reveal what each expert actually encodes. We train sparsely-gated convoluti…