Search Results for author: Yunpu Ma

Found 40 papers, 18 papers with code

Learning Neural Ordinary Equations for Forecasting Future Links on Temporal Knowledge Graphs

no code implementations EMNLP 2021 Zhen Han, Zifeng Ding, Yunpu Ma, Yujia Gu, Volker Tresp

In addition, a novel graph transition layer is applied to capture the transitions on the dynamic graph, i. e., edge formation and dissolution.

Knowledge Graphs

TempCaps: A Capsule Network-based Embedding Model for Temporal Knowledge Graph Completion

1 code implementation spnlp (ACL) 2022 Guirong Fu, Zhao Meng, Zhen Han, Zifeng Ding, Yunpu Ma, Matthias Schubert, Volker Tresp, Roger Wattenhofer

In this paper, we tackle the temporal knowledge graph completion task by proposing TempCaps, which is a Capsule network-based embedding model for Temporal knowledge graph completion.

Entity Embeddings Temporal Knowledge Graph Completion

Quantum Architecture Search with Unsupervised Representation Learning

no code implementations21 Jan 2024 Yize Sun, Zixin Wu, Yunpu Ma, Volker Tresp

Most QAS algorithms combine their search space and search algorithms together and thus generally require evaluating a large number of quantum circuits during the search process.

Bayesian Optimization Neural Architecture Search +1

zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models

1 code implementation15 Nov 2023 Zifeng Ding, Heling Cai, Jingpei Wu, Yunpu Ma, Ruotong Liao, Bo Xiong, Volker Tresp

We first input the text descriptions of KG relations into large language models (LLMs) for generating relation representations, and then introduce them into embedding-based TKGF methods.

Knowledge Graphs Relation +1

GraphextQA: A Benchmark for Evaluating Graph-Enhanced Large Language Models

1 code implementation12 Oct 2023 Yuanchun Shen, Ruotong Liao, Zhen Han, Yunpu Ma, Volker Tresp

The proposed dataset is designed to evaluate graph-language models' ability to understand graphs and make use of it for answer generation.

Answer Generation Hallucination +3

GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models

1 code implementation11 Oct 2023 Ruotong Liao, Xu Jia, Yangzhe Li, Yunpu Ma, Volker Tresp

Extensive experiments have shown that GenTKG outperforms conventional methods of temporal relational forecasting with low computation resources using extremely limited training data as few as 16 samples.

Retrieval

Differentiable Quantum Architecture Search for Quantum Reinforcement Learning

no code implementations19 Sep 2023 Yize Sun, Yunpu Ma, Volker Tresp

However, the pre-defined circuit needs more flexibility for different tasks, and the circuit design based on various datasets could become intractable in the case of a large circuit.

Q-Learning Quantum Machine Learning +1

Improving Few-Shot Inductive Learning on Temporal Knowledge Graphs using Confidence-Augmented Reinforcement Learning

1 code implementation2 Apr 2023 Zifeng Ding, Jingpei Wu, Zongyue Li, Yunpu Ma, Volker Tresp

Most previous TKGC methods only consider predicting the missing links among the entities seen in the training set, while they are unable to achieve great performance in link prediction concerning newly-emerged unseen entities.

Few-Shot Learning Link Prediction +1

Few-Shot Inductive Learning on Temporal Knowledge Graphs using Concept-Aware Information

no code implementations15 Nov 2022 Zifeng Ding, Jingpei Wu, Bailan He, Yunpu Ma, Zhen Han, Volker Tresp

Similar problem exists in temporal knowledge graphs (TKGs), and no previous temporal knowledge graph completion (TKGC) method is developed for modeling newly-emerged entities.

Link Prediction Meta-Learning +1

Learning Meta Representations of One-shot Relations for Temporal Knowledge Graph Link Prediction

no code implementations21 May 2022 Zifeng Ding, Bailan He, Yunpu Ma, Zhen Han, Volker Tresp

In this paper, we follow the previous work that focuses on few-shot relational learning on static KGs and extend two fundamental TKG reasoning tasks, i. e., interpolated and extrapolated link prediction, to the one-shot setting.

Few-Shot Learning Knowledge Graphs +2

Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion

no code implementations24 Apr 2022 Feifei Xu, Shanlin Zhou, Xinpeng Wang, Yunpu Ma, Wenkai Zhang, Zhisong Li

To merge these two forms of knowledge into the dialogue effectively, we design a dynamic virtual knowledge selector and a controller that help to enrich and expand knowledge space.

Dialogue Generation Informativeness +1

TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs

1 code implementation15 Dec 2021 Yushan Liu, Yunpu Ma, Marcel Hildebrandt, Mitchell Joblin, Volker Tresp

Conventional static knowledge graphs model entities in relational data as nodes, connected by edges of specific relation types.

Knowledge Graphs Link Prediction

A Simple But Powerful Graph Encoder for Temporal Knowledge Graph Completion

no code implementations14 Dec 2021 Zifeng Ding, Yunpu Ma, Bailan He, Volker Tresp

Knowledge graphs contain rich knowledge about various entities and the relational information among them, while temporal knowledge graphs (TKGs) describe and model the interactions of the entities over time.

Temporal Knowledge Graph Completion

APPTeK: Agent-Based Predicate Prediction in Temporal Knowledge Graphs

no code implementations27 Oct 2021 Christian M. M. Frey, Yunpu Ma, Matthias Schubert

In temporal Knowledge Graphs (tKGs), the temporal dimension is attached to facts in a knowledge base resulting in quadruples between entities such as (Nintendo, released, Super Mario, Sep-13-1985), where the predicate holds within a time interval or at a timestamp.

Knowledge Graphs reinforcement-learning +1

SEA: Graph Shell Attention in Graph Neural Networks

no code implementations20 Oct 2021 Christian M. M. Frey, Yunpu Ma, Matthias Schubert

Intuitively, by increasing the number of experts, the models gain in expressiveness such that a node's representation is solely based on nodes that are located within the receptive field of an expert.

The Tensor Brain: A Unified Theory of Perception, Memory and Semantic Decoding

1 code implementation27 Sep 2021 Volker Tresp, Sahand Sharifzadeh, Hang Li, Dario Konopatzki, Yunpu Ma

Although memory appears to be about the past, its main purpose is to support the agent in the present and the future.

Decision Making Self-Supervised Learning

TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting

1 code implementation EMNLP 2021 Haohai Sun, Jialun Zhong, Yunpu Ma, Zhen Han, Kun He

Compared with the completion task, the forecasting task is more difficult that faces two main challenges: (1) how to effectively model the time information to handle future timestamps?

Link Prediction reinforcement-learning +1

Adaptive Multi-Resolution Attention with Linear Complexity

no code implementations10 Aug 2021 Yao Zhang, Yunpu Ma, Thomas Seidl, Volker Tresp

Transformers have improved the state-of-the-art across numerous tasks in sequence modeling.

Temporal Knowledge Graph Forecasting with Neural ODE

1 code implementation13 Jan 2021 Zhen Han, Zifeng Ding, Yunpu Ma, Yujia Gu, Volker Tresp

In addition, a novel graph transition layer is applied to capture the transitions on the dynamic graph, i. e., edge formation and dissolution.

Future prediction Knowledge Graphs

Contrastive Learning for Recommender System

no code implementations5 Jan 2021 Zhuang Liu, Yunpu Ma, Yuanxin Ouyang, Zhang Xiong

To solve this problem, we propose a graph contrastive learning module for a general recommender system that learns the embeddings in a self-supervised manner and reduces the randomness of message dropout.

Collaborative Filtering Contrastive Learning +3

KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation

1 code implementation ACL 2021 Yiran Xing, Zai Shi, Zhao Meng, Gerhard Lakemeyer, Yunpu Ma, Roger Wattenhofer

We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts.

Knowledge Graphs Language Modelling

Controllable Multi-Character Psychology-Oriented Story Generation

1 code implementation11 Oct 2020 Feifei Xu, Xinpeng Wang, Yunpu Ma, Volker Tresp, Yuyi Wang, Shanlin Zhou, Haizhou Du

In our work, we aim to design an emotional line for each character that considers multiple emotions common in psychological theories, with the goal of generating stories with richer emotional changes in the characters.

Sentence Story Generation

Learning Individualized Treatment Rules with Estimated Translated Inverse Propensity Score

1 code implementation2 Jul 2020 Zhiliang Wu, Yinchong Yang, Yunpu Ma, Yushan Liu, Rui Zhao, Michael Moor, Volker Tresp

Randomized controlled trials typically analyze the effectiveness of treatments with the goal of making treatment recommendations for patient subgroups.

Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs

1 code implementation AKBC 2020 Zhen Han, Yunpu Ma, Yuyi Wang, Stephan Günnemann, Volker Tresp

The Hawkes process has become a standard method for modeling self-exciting event sequences with different event types.

Knowledge Graphs

Causal Inference under Networked Interference and Intervention Policy Enhancement

no code implementations20 Feb 2020 Yunpu Ma, Volker Tresp

After deriving causal effect estimators, we further study intervention policy improvement on the graph under capacity constraint.

Causal Inference

The Tensor Brain: Semantic Decoding for Perception and Memory

no code implementations29 Jan 2020 Volker Tresp, Sahand Sharifzadeh, Dario Konopatzki, Yunpu Ma

In particular, we propose that explicit perception and declarative memories require a semantic decoder, which, in a simple realization, is based on four layers: First, a sensory memory layer, as a buffer for sensory input, second, an index layer representing concepts, third, a memoryless representation layer for the broadcasting of information ---the "blackboard", or the "canvas" of the brain--- and fourth, a working memory layer as a processing center and data buffer.

Knowledge Graphs

Debate Dynamics for Human-comprehensible Fact-checking on Knowledge Graphs

no code implementations9 Jan 2020 Marcel Hildebrandt, Jorge Andres Quintero Serna, Yunpu Ma, Martin Ringsquandl, Mitchell Joblin, Volker Tresp

The underlying idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments -- paths in the knowledge graph -- with the goal to justify the fact being true (thesis) or the fact being false (antithesis), respectively.

Common Sense Reasoning Fact Checking +3

Quantum Machine Learning Algorithm for Knowledge Graphs

no code implementations4 Jan 2020 Yunpu Ma, Volker Tresp

We simplify the problem by making a plausible assumption that the tensor representation of a knowledge graph can be approximated by its low-rank tensor singular value decomposition, which is verified by our experiments.

BIG-bench Machine Learning Knowledge Graphs +1

Reasoning on Knowledge Graphs with Debate Dynamics

2 code implementations2 Jan 2020 Marcel Hildebrandt, Jorge Andres Quintero Serna, Yunpu Ma, Martin Ringsquandl, Mitchell Joblin, Volker Tresp

The main idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments -- paths in the knowledge graph -- with the goal to promote the fact being true (thesis) or the fact being false (antithesis), respectively.

General Classification Knowledge Graphs +2

Variational Quantum Circuit Model for Knowledge Graphs Embedding

no code implementations19 Feb 2019 Yunpu Ma, Volker Tresp, Liming Zhao, Yuyi Wang

In this work, we propose the first quantum Ans\"atze for the statistical relational learning on knowledge graphs using parametric quantum circuits.

Knowledge Graph Embedding Knowledge Graphs +2

Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions

no code implementations1 Sep 2018 Stephan Baier, Yunpu Ma, Volker Tresp

In this paper we consider scene descriptions which are represented as a set of triples (subject, predicate, object), where each triple consists of a pair of visual objects, which appear in the image, and the relationship between them (e. g. man-riding-elephant, man-wearing-hat).

Link Prediction object-detection +3

Improving Information Extraction from Images with Learned Semantic Models

no code implementations27 Aug 2018 Stephan Baier, Yunpu Ma, Volker Tresp

Many applications require an understanding of an image that goes beyond the simple detection and classification of its objects.

General Classification Relationship Detection +1

Embedding Models for Episodic Knowledge Graphs

no code implementations30 Jun 2018 Yunpu Ma, Volker Tresp, Erik Daxberger

In this paper, we extend models for static knowledge graphs to temporal knowledge graphs.

Knowledge Graph Embeddings Knowledge Graphs

The Tensor Memory Hypothesis

no code implementations9 Aug 2017 Volker Tresp, Yunpu Ma

We show how episodic memory and semantic memory can be realized and discuss how new memory traces can be generated from sensory input: Existing memories are the basis for perception and new memories are generated via perception.

Cannot find the paper you are looking for? You can Submit a new open access paper.