613 citations · 1.1k across the 36 of their papers we have counts for
13 papers · 1 filter
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Mind Lab, :, Vin Bo +80
Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized arou…
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
Mind Lab, :, Vin Bo +64
Parameter-efficient fine-tuning (PEFT) is usually treated as a cheaper alternative to full fine-tuning. We study a broader role: small trainable adapters as persistent local state…
MinT: Managed Infrastructure for Training and Serving Millions of LLMs
Mind Lab, :, Song Cao +60
We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a setting where many trained polici…
ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction
Yaorui Shi, An Zhang, Enzhi Zhang +2
Predicting chemical reactions, a fundamental challenge in chemistry, involves forecasting the resulting products from a given reaction process. Conventional techniques, notably tho…
Robust Collaborative Filtering to Popularity Distribution Shift
An Zhang, Wenchang Ma, Jingnan Zheng +2
In leading collaborative filtering (CF) models, representations of users and items are prone to learn popularity bias in the training data as shortcuts. The popularity shortcut tri…
Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules
Zhiyuan Liu, Yaorui Shi, An Zhang +4
Masked graph modeling excels in the self-supervised representation learning of molecular graphs. Scrutinizing previous studies, we can reveal a common scheme consisting of three ke…
Discovering Dynamic Causal Space for DAG Structure Learning
Fangfu Liu, Wenchang Ma, An Zhang +3
Discovering causal structure from purely observational data (i.e., causal discovery), aiming to identify causal relationships among variables, is a fundamental task in machine lear…
Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting
An Zhang, Fangfu Liu, Wenchang Ma +3
Under stringent model type and variable distribution assumptions, differentiable score-based causal discovery methods learn a directed acyclic graph (DAG) from observational data b…
Let Invariant Rationale Discovery Inspire Graph Contrastive Learning
Sihang Li, Xiang Wang, An zhang +3
Leading graph contrastive learning (GCL) methods perform graph augmentations in two fashions: (1) randomly corrupting the anchor graph, which could cause the loss of semantic infor…
Differentiable Invariant Causal Discovery
Yu Wang, An Zhang, Xiang Wang +3
Learning causal structure from observational data is a fundamental challenge in machine learning. However, the majority of commonly used differentiable causal discovery methods are…
Reinforced Causal Explainer for Graph Neural Networks
Xiang Wang, Yingxin Wu, An Zhang +3
Explainability is crucial for probing graph neural networks (GNNs), answering questions like "Why the GNN model makes a certain prediction?". Feature attribution is a prevalent tec…
Deconfounding to Explanation Evaluation in Graph Neural Networks
Ying-Xin Wu, Xiang Wang, An Zhang +4
Explainability of graph neural networks (GNNs) aims to answer "Why the GNN made a certain prediction?", which is crucial to interpret the model prediction. The feature attribution…
Discovering Invariant Rationales for Graph Neural Networks
Ying-Xin Wu, Xiang Wang, An Zhang +2
Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features -- rationale -- which guides the model prediction. Unfortunately,…