Related papers: Text Grafting: Near-Distribution Weak Supervision …

Large Language Models (LLMs) have shown strong performance on text-attributed graphs (TAGs) due to their superior semantic understanding ability on textual node features. However, their effectiveness as predictors in the low-resource…

Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP. Nonetheless, their development has happened in isolation, while the…

Semi-supervised semantic segmentation relieves the reliance on large-scale labeled data by leveraging unlabeled data. Recent semi-supervised semantic segmentation approaches mainly resort to pseudo-labeling methods to exploit unlabeled…

Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts…

Weakly-supervised text classification trains a classifier using the label name of each target class as the only supervision, which largely reduces human annotation efforts. Most existing methods first use the label names as static…

We study open-world multi-label text classification under extremely weak supervision (XWS), where the user only provides a brief description for classification objectives without any labels or ground-truth label space. Similar single-label…

Creating labeled training sets has become one of the major roadblocks in machine learning. To address this, recent \emph{Weak Supervision (WS)} frameworks synthesize training labels from multiple potentially noisy supervision sources.…

What sorts of structure might enable a learner to discover classes from unlabeled data? Traditional approaches rely on feature-space similarity and heroic assumptions on the data. In this paper, we introduce unsupervised learning under…

The widespread use of Large Language Models (LLMs), celebrated for their ability to generate human-like text, has raised concerns about misinformation and ethical implications. Addressing these concerns necessitates the development of…

As one of the most exciting features of large language models (LLMs), in-context learning is a mixed blessing. While it allows users to fast-prototype a task solver with only a few training examples, the performance is generally sensitive…

Supervised learning usually requires a large amount of labelled data. However, attaining ground-truth labels is costly for many tasks. Alternatively, weakly supervised methods learn with cheap weak signals that only approximately label some…

Scribble-based weakly-supervised semantic segmentation using sparse scribble supervision is gaining traction as it reduces annotation costs when compared to fully annotated alternatives. Existing methods primarily generate pseudo-labels by…

Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existing research on MeanFlow primarily focuses on class-to-image generation. However, an…

Weakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data. Recent research shows that keyword-driven methods can achieve state-of-the-art performance on various tasks. However, these…

Federated Graph Learning (FGL) enables privacy-preserving, distributed training of graph neural networks without sharing raw data. Among its approaches, subgraph-FL has become the dominant paradigm, with most work focused on improving…

Few-shot node classification is tasked to provide accurate predictions for nodes from novel classes with only few representative labeled nodes. This problem has drawn tremendous attention for its projection to prevailing real-world…

Graphs are growing rapidly, along with the number of distinct label categories associated with them. Applications like e-commerce, healthcare, recommendation systems, and various social media platforms are rapidly moving towards graph…

Short-text classification, like all data science, struggles to achieve high performance using limited data. As a solution, a short sentence may be expanded with new and relevant feature words to form an artificially enlarged dataset, and…

While great success has been achieved in building vision models with Contrastive Language-Image Pre-training (CLIP) over internet-scale image-text pairs, building transferable Graph Neural Networks (GNNs) with CLIP pipeline is challenging…

Graph-language models (GLMs) have demonstrated great potential in graph-based semi-supervised learning. A typical GLM consists of two key stages: graph generation and text embedding, which are usually implemented by inferring a latent graph…