11 citations · 20 across the 4 of their papers we have counts for
4 papers
Transformers learn to implement preconditioned gradient descent for in-context learning
Kwangjun Ahn, Xiang Cheng, Hadi Daneshmand +1
Several recent works demonstrate that transformers can implement algorithms like gradient descent. By a careful construction of weights, these works show that multiple layers of tr…
Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System
Xiangming Gu, Xiang Cheng
Deep neural networks (DNNs) demonstrate great success in classification tasks. However, they act as black boxes and we don't know how they make decisions in a particular classifica…
Cooperative Reasoning on Knowledge Graph and Corpus: A Multi-agentReinforcement Learning Approach
Yunan Zhang, Xiang Cheng, Heting Gao +1
Knowledge-graph-based reasoning has drawn a lot of attention due to its interpretability. However, previous methods suffer from the incompleteness of the knowledge graph, namely th…
Learning to Order Sub-questions for Complex Question Answering
Yunan Zhang, Xiang Cheng, Yufeng Zhang +5
Answering complex questions involving multiple entities and relations is a challenging task. Logically, the answer to a complex question should be derived by decomposing the comple…