Search Results for author:
Found 187 papers, 119 papers with code
Re-examining the Role of Schema Linking in Text-to-SQL
By providing a schema linking corpus based on the Spider text-to-SQL dataset, we systematically study the role of schema linking.
Learning to Imagine: Integrating Counterfactual Thinking in Neural Discrete Reasoning
Neural discrete reasoning (NDR) has shown remarkable progress in combining deep models with discrete reasoning.
Progressive Text-to-3D Generation for Automatic 3D Prototyping
We aspire for our work to pave the way for automatic 3D prototyping via natural language descriptions.
NExT-GPT: Any-to-Any Multimodal LLM
While recently Multimodal Large Language Models (MM-LLMs) have made exciting strides, they mostly fall prey to the limitation of only input-side multimodal understanding, without the ability to produce content in multiple modalities.
Empowering Dynamics-aware Text-to-Video Diffusion with Large Language Models
In this work, we investigate strengthening the awareness of video dynamics for DMs, for high-quality T2V generation.
Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction
The hierarchical VAE allows us to learn the complex and low-level latent variables for stock prediction, while the diffusion probabilistic model trains the predictor to handle stock price stochasticity by progressively adding random noise to the stock data.
Context-aware Event Forecasting via Graph Disentanglement
The task of event forecasting aims to model the relational and temporal patterns based on historical events and makes forecasting to what will happen in the future.
Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling
A scene-event mapping mechanism is first designed to bridge the gap between the underlying scene structure and the high-level event semantic structure, resulting in an overall hierarchical scene-event (termed ICE) graph structure.
LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation
Afterward, we propose a fine-grained object-interaction diffusion method to synthesize high-faithfulness images conditioned on the prompt and the automatically generated layout.
Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition
On the other hand, during the feature fusion stage, we propose a Contribution-aware Fusion Mechanism (CFM) and a Context Refusion Mechanism (CRM) for multimodal and context integration, respectively.
Empowering Vision-Language Models to Follow Interleaved Vision-Language Instructions
To address this issue, we propose a generic and lightweight controllable knowledge re-injection module, which utilizes the sophisticated reasoning ability of LLMs to control the VPG to conditionally extract instruction-specific visual information and re-inject it into the LLM.
Redundancy-aware Transformer for Video Question Answering
This paper identifies two kinds of redundancy in the current VideoQA paradigm.
SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning
More recently, with the rapid development of language models (LMs), researchers have focused on leveraging LMs to facilitate the learning of TGs, either by jointly training them in a computationally intensive framework (merging the two stages), or designing complex self-supervised training tasks for feature extraction (enhancing the first stage).
Ranked #1 on
Node Property Prediction
on ogbn-arxiv
XNLP: An Interactive Demonstration System for Universal Structured NLP
Structured Natural Language Processing (XNLP) is an important subset of NLP that entails understanding the underlying semantic or syntactic structure of texts, which serves as a foundational component for many downstream applications.
Discovering Spatio-Temporal Rationales for Video Question Answering
We then conduct extensive studies to verify the importance of STR as well as the proposed answer interaction mechanism.
Revisiting Conversation Discourse for Dialogue Disentanglement
Conversation utterances are essentially organized and described by the underlying discourse, and thus dialogue disentanglement requires the full understanding and harnessing of the intrinsic discourse attribute.
Computational Technologies for Fashion Recommendation: A Survey
the computational technologies of fashion recommendation.
Discovering Dynamic Causal Space for DAG Structure Learning
Discovering causal structure from purely observational data (i. e., causal discovery), aiming to identify causal relationships among variables, is a fundamental task in machine learning.
LLMDet: A Large Language Models Detection Tool
With the advancement of generative language models, the generated text has come remarkably close to high-quality human-authored text in terms of fluency and diversity.
Robust Instruction Optimization for Large Language Models with Distribution Shifts
Large Language Models have demonstrated significant ability in accomplishing a wide range of Natural Language Processing (NLP) tasks.
Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration
Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation.
MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space
Multi-aspect controllable text generation aims to generate fluent sentences that possess multiple desired attributes simultaneously.
InstructVid2Vid: Controllable Video Editing with Natural Language Instructions
To improve the consistency between adjacent frames of generated videos, we propose the Frame Difference Loss, which is incorporated during the training process.
Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination
In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup, inference-time image-free UMMT, where the model is trained with source-text image pairs, and tested with only source-text inputs.
Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction
Latest efforts on cross-lingual relation extraction (XRE) aggressively leverage the language-consistent structural features from the universal dependency (UD) resource, while they may largely suffer from biased transfer (e. g., either target-biased or source-biased) due to the inevitable linguistic disparity between languages.
Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment
Unpaired cross-lingual image captioning has long suffered from irrelevancy and disfluency issues, due to the inconsistencies of the semantic scene and syntax attributes during transfer.
Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling
First, we represent the fine-grained semantic structures of the input image and text with the visual and textual scene graphs, which are further fused into a unified cross-modal graph (CMG).
Generating Visual Spatial Description via Holistic 3D Scene Understanding
With an external 3D scene extractor, we obtain the 3D objects and scene features for input images, based on which we construct a target object-centered 3D spatial scene graph (Go3D-S2G), such that we model the spatial semantics of target objects within the holistic 3D scenes.
Reasoning Implicit Sentiment with Chain-of-Thought Prompting
While sentiment analysis systems try to determine the sentiment polarities of given targets based on the key opinion expressions in input texts, in implicit sentiment analysis (ISA) the opinion cues come in an implicit and obscure manner.
Dual Semantic Knowledge Composed Multimodal Dialog Systems
Thereafter, considering that the attribute knowledge and relation knowledge can benefit the responding to different levels of questions, we design a multi-level knowledge composition module in MDS-S2 to obtain the latent composed response representation.
A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects
Proactive dialogue systems, related to a wide range of real-world conversational applications, equip the conversational agent with the capability of leading the conversation direction towards achieving pre-defined targets or fulfilling certain goals from the system side.
Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents with Semantic-Oriented Hierarchical Graphs
Discrete reasoning over table-text documents (e. g., financial reports) gains increasing attention in recent two years.
Transfer Visual Prompt Generator across LLMs
While developing a new vision-language LLM (VL-LLM) by pre-training on tremendous image-text pairs from scratch can be exceedingly resource-consuming, connecting an existing LLM with a comparatively lightweight visual prompt generator (VPG) becomes a feasible paradigm.
Search-in-the-Chain: Towards Accurate, Credible and Traceable Large Language Models for Knowledge-intensive Tasks
Second, IR verifies the answer of each node of CoQ, it corrects the answer that is not consistent with the retrieved information when IR gives high confidence, which improves the credibility.
Learnable Pillar-based Re-ranking for Image-Text Retrieval
Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities.
On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training
In this study, we propose to enhance the ABSA robustness by systematically rethinking the bottlenecks from all possible angles, including model, data, and training.
Aspect-Based Sentiment Analysis (ABSA)
Contrastive Learning
+1
LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model
Universally modeling all typical information extraction tasks (UIE) with one generative language model (GLM) has revealed great potential by the latest study, where various IE predictions are unified into a linearized hierarchical expression under a GLM.
Diffusion Recommender Model
In light of the impressive advantages of Diffusion Models (DMs) over traditional generative models in image synthesis, we propose a novel Diffusion Recommender Model (named DiffRec) to learn the generative process in a denoising manner.
Generative Recommendation: Towards Next-generation Recommender Paradigm
However, such a retrieval-based recommender paradigm faces two limitations: 1) the human-generated items in the corpus might fail to satisfy the users' diverse information needs, and 2) users usually adjust the recommendations via passive and inefficient feedback such as clicks.
Causal Disentangled Recommendation Against User Preference Shifts
Inspired by the causal graph, our key considerations to handle preference shifts lie in modeling the interaction generation procedure by: 1) capturing the preference shifts across environments for accurate preference prediction, and 2) disentangling the sparse influence from user preference to interactions for accurate effect estimation of preference.
Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models
Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen pre-training models.
Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting
Despite great success in low-dimensional linear systems, it has been observed that these approaches overly exploit easier-to-fit samples, thus inevitably learning spurious edges.
Contrastive Video Question Answering via Video Graph Transformer
CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations and dynamics, for complex spatio-temporal reasoning.
Ranked #2 on
Video Question Answering
on NExT-QA
(using extra training data)
Invariant Collaborative Filtering to Popularity Distribution Shift
Collaborative Filtering (CF) models, despite their great success, suffer from severe performance drops due to popularity distribution shifts, where these changes are ubiquitous and inevitable in real-world scenarios.
Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding
To systematically benchmark the compositional generalizability of temporal grounding models, we introduce a new Compositional Temporal Grounding task and construct two new dataset splits, i. e., Charades-CG and ActivityNet-CG.
Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning
Moreover, we treat the uncertainty score of frames in a video as a whole, and estimate the difficulty of each video, which can further relieve the burden of video selection.
MRTNet: Multi-Resolution Temporal Network for Video Sentence Grounding
In this work, we propose a novel multi-resolution temporal video sentence grounding network: MRTNet, which consists of a multi-modal feature encoder, a Multi-Resolution Temporal (MRT) module, and a predictor module.
Causal Inference for Knowledge Graph based Recommendation
Knowledge Graph (KG), as a side-information, tends to be utilized to supplement the collaborative filtering (CF) based recommendation model.
Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark
In particular, the text description provides a dense semantic description guidance for the primary context of the traffic scene, while the driver attention provides a traction to focus on the critical region closely correlating with safe driving.
Visually Grounded Commonsense Knowledge Acquisition
In this work, we present CLEVER, which formulates CKE as a distantly supervised multi-instance learning problem, where models learn to summarize commonsense relations from a bag of images about an entity pair without any human annotation on image instances.
Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization
The key idea underpinning the proposed method is to integrate fine- and coarse-grained retrieval as matching data points with small and large fluctuations, respectively.
Composed Image Retrieval (CoIR)
Image Retrieval with Multi-Modal Query
+1
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
In an attempt to fill this gap, we propose a unified pixel- and patch-wise self-supervised learning framework, called PiPa, for domain adaptive semantic segmentation that facilitates intra-image pixel-wise correlations and patch-wise semantic consistency against different contexts.
Ranked #1 on
Semantic Segmentation
on SYNTHIA-to-Cityscapes
DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis
The rapid development of aspect-based sentiment analysis (ABSA) within recent decades shows great potential for real-world society.
Aspect-Based Sentiment Analysis (ABSA)
Conversational Sentiment Quadruple Extraction
+1
Behavioral Intention Prediction in Driving Scenes: A Survey
In the driving scene, the road participants usually show frequent interaction and intention understanding with the surrounding.
Incorporating Bias-aware Margins into Contrastive Loss for Collaborative Filtering
Collaborative filtering (CF) models easily suffer from popularity bias, which makes recommendation deviate from users' actual preferences.
PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance
To facilitate conversational question answering (CQA) over hybrid contexts in finance, we present a new dataset, named PACIFIC.
ConReader: Exploring Implicit Relations in Contracts for Contract Clause Extraction
We study automatic Contract Clause Extraction (CCE) by modeling implicit relations in legal contracts.
Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendation
Specifically, Re4 encapsulates three backward flows, i. e., 1) Re-contrast, which drives each interest embedding to be distinct from other interests using contrastive learning; 2) Re-attend, which ensures the interest-item correlation estimation in the forward flow to be consistent with the criterion used in final recommendation; and 3) Re-construct, which ensures that each interest embedding can semantically reflect the information of representative items that relate to the corresponding interest.
CCL4Rec: Contrast over Contrastive Learning for Micro-video Recommendation
Micro-video recommender systems suffer from the ubiquitous noises in users' behaviors, which might render the learned user representation indiscriminating, and lead to trivial recommendations (e. g., popular items) or even weird ones that are far beyond users' interests.
Equivariant and Invariant Grounding for Video Question Answering
Specifically, the equivariant grounding encourages the answering to be sensitive to the semantic changes in the causal scene and question; in contrast, the invariant grounding enforces the answering to be insensitive to the changes in the environment scene.
Towards Complex Document Understanding By Discrete Reasoning
Document Visual Question Answering (VQA) aims to understand visually-rich documents to answer questions in natural language, which is an emerging research topic for both Natural Language Processing and Computer Vision.
Video Graph Transformer for Video Question Answering
VGT's uniqueness are two-fold: 1) it designs a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations, and dynamics for complex spatio-temporal reasoning; and 2) it exploits disentangled video and text Transformers for relevance comparison between the video and text to perform QA, instead of entangled cross-modal Transformer for answer classification.
Ranked #8 on
Video Question Answering
on NExT-QA
(using extra training data)
Structured and Natural Responses Co-generation for Conversational Search
Existing approaches either 1) predict structured dialog acts first and then generate natural response; or 2) map conversation context to natural responses directly in an end-to-end manner.
Intelligent Request Strategy Design in Recommender System
RSs typically put a large number of items into one page to reduce excessive resource consumption from numerous paging requests, which, however, would diminish the RSs' ability to timely renew the recommendations according to users' real-time interest and lead to a poor user experience.
Let Invariant Rationale Discovery Inspire Graph Contrastive Learning
Specifically, without supervision signals, RGCL uses a rationale generator to reveal salient features about graph instance-discrimination as the rationale, and then creates rationale-aware views for contrastive learning.
Invariant Grounding for Video Question Answering
At its core is understanding the alignments between visual scenes in video and linguistic semantics in question to yield the answer.
CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation
Recent methods usually take advantage of both user-bundle and user-item interactions information to obtain informative representations for users and bundles, corresponding to bundle view and item view, respectively.
Differentiable Invariant Causal Discovery
This paper proposes Differentiable Invariant Causal Discovery (DICD), utilizing the multi-environment information based on a differentiable framework to avoid learning spurious edges and wrong causal directions.
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
We show that PEVL enables state-of-the-art performance of detector-free VLP models on position-sensitive tasks such as referring expression comprehension and phrase grounding, and also improves the performance on position-insensitive tasks with grounded inputs.
Ranked #1 on
Visual Question Answering (VQA)
on GQA
3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective
This research aims to study a self-supervised 3D clothing reconstruction method, which recovers the geometry shape and texture of human clothing from a single image.
Ranked #1 on
Single-View 3D Reconstruction
on ATR
Reinforced Causal Explainer for Graph Neural Networks
Such reward accounts for the dependency of the newly-added edge and the previously-added edges, thus reflecting whether they collaborate together and form a coalition to pursue better explanations.
Multiple-environment Self-adaptive Network for Aerial-view Geo-localization
This task is mostly regarded as an image retrieval problem.
A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems
In this work, we propose a novel Unified MultI-goal conversational recommeNDer system, namely UniMIND.
Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy
To this end, we contribute to advance the study of the proactive dialogue policy to a more natural and challenging setting, i. e., interacting dynamically with users.
Fine-Grained Scene Graph Generation with Data Transfer
Scene graph generation (SGG) is designed to extract (subject, predicate, object) triplets in images.
Ranked #1 on
Predicate Classification
on Visual Genome
Video Question Answering: Datasets, Algorithms and Challenges
Video Question Answering (VideoQA) aims to answer natural language questions according to the given videos.
KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems
The progress of recommender systems is hampered mainly by evaluation as it requires real-time interactions between humans and systems, which is too laborious and expensive.
Discovering Invariant Rationales for Graph Neural Networks
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.
Deconfounding to Explanation Evaluation in Graph Neural Networks
In this work, we propose Deconfounded Subgraph Evaluation (DSE) which assesses the causal effect of an explanatory subgraph on the model prediction.
A Dual Prompt Learning Framework for Few-Shot Dialogue State Tracking
In this paper, we focus on how to utilize the language understanding and generation ability of pre-trained language models for DST.
Training Free Graph Neural Networks for Graph Matching
We present a framework of Training Free Graph Matching (TFGM) to boost the performance of Graph Neural Networks (GNNs) based graph matching, providing a fast promising solution without training (training-free).
Causal Attention for Interpretable and Generalizable Graph Classification
To endow the classifier with better interpretation and generalization, we propose the Causal Attention Learning (CAL) strategy, which discovers the causal patterns and mitigates the confounding effect of shortcuts.
Video as Conditional Graph Hierarchy for Multi-Granular Question Answering
To align with the multi-granular essence of linguistic concepts in language queries, we propose to model video as a conditional graph hierarchy which weaves together visual facts of different granularity in a level-wise manner, with the guidance of corresponding textual cues.
Ranked #13 on
Video Question Answering
on NExT-QA
Rethinking the Two-Stage Framework for Grounded Situation Recognition
Since each verb is associated with a specific set of semantic roles, all existing GSR methods resort to a two-stage framework: predicting the verb in the first stage and detecting the semantic roles in the second stage.
Ranked #2 on
Situation Recognition
on imSitu
Learning Robust Recommender from Noisy Implicit Feedback
Inspired by this observation, we propose a new training strategy named Adaptive Denoising Training (ADT), which adaptively prunes the noisy interactions by two paradigms (i. e., Truncated Loss and Reweighted Loss).
Towards Multi-Grained Explainability for Graph Neural Networks
A performant paradigm towards multi-grained explainability is until-now lacking and thus a focus of our work.
Inductive Lottery Ticket Learning for Graph Neural Networks
In this work, we propose a simple and effective learning paradigm, Inductive Co-Pruning of GNNs (ICPG), to endow graph lottery tickets with inductive pruning capacity.
Decoupling Strategy and Surface Realization for Task-oriented Dialogues
The core is to construct a latent content space for strategy optimization and disentangle the surface style from it.
Why Do We Click: Visual Impression-aware News Recommendation
In this work, inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news, we propose to capture such visual impression information with visual-semantic modeling for news recommendation.
CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models
Pre-Trained Vision-Language Models (VL-PTMs) have shown promising capabilities in grounding natural language in image data, facilitating a broad variety of cross-modal tasks.
CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation
In this paper, we propose to learn accurate and robust user representations, which are required to be less sensitive to (attack on) noisy behaviors and trust more on the indispensable ones, by modeling counterfactual data distribution.
How Knowledge Graph and Attention Help? A Qualitative Analysis into Bag-level Relation Extraction
In this paper, we contribute a dataset and propose a paradigm to quantitatively evaluate the effect of attention and KG on bag-level relation extraction (RE).
How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction
In this paper, we contribute a dataset and propose a paradigm to quantitatively evaluate the effect of attention and KG on bag-level relation extraction (RE).
Contrastive Learning for Cold-Start Recommendation
It aims to maximize the mutual dependencies between item content and collaborative signals.
MConv: An Environment for Multimodal Conversational Search across Multiple Domains
Second, a set of benchmark results for dialogue state tracking, conversational recommendation, response generation as well as a unified model for multiple tasks are reported.
Ranked #2 on
Dialogue State Tracking
on MMConv
Affective Image Content Analysis: Two Decades Review and New Perspectives
Images can convey rich semantics and induce various emotions in viewers.
NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions
We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions.
Empowering Language Understanding with Counterfactual Reasoning
Present language understanding methods have demonstrated extraordinary ability of recognizing patterns in texts via machine learning.
Deconfounded Video Moment Retrieval with Causal Intervention
To fill the research gap, we propose a causality-inspired VMR framework that builds structural causal model to capture the true effect of query and video content on the prediction.
Reproducibility Companion Paper: Knowledge Enhanced Neural Fashion Trend Forecasting
This companion paper supports the replication of the fashion trend forecasting experiments with the KERN (Knowledge Enhanced Recurrent Network) method that we presented in the ICMR 2020.
Deconfounded Recommendation for Alleviating Bias Amplification
In this work, we scrutinize the cause-effect factors for bias amplification, identifying the main reason lies in the confounder effect of imbalanced item distribution on user representation and prediction score.
NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions
We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions.
Leveraging Two Types of Global Graph for Sequential Fashion Recommendation
Sequential fashion recommendation is of great significance in online fashion shopping, which accounts for an increasing portion of either fashion retailing or online e-commerce.
TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance
In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions.
Ranked #1 on
Question Answering
on TAT-QA
Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction
Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills.
Ranked #1 on
Grammatical Error Detection
on FCE
Leveraging Multiple Relations for Fashion Trend Forecasting Based on Social Media
Towards insightful fashion trend forecasting, previous work [1] proposed to analyze more fine-grained fashion elements which can informatively reveal fashion trends.
A-FMI: Learning Attributions from Deep Networks via Feature Map Importance
Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs).
Conditional Hyper-Network for Blind Super-Resolution with Multiple Degradations
We extract degradation prior at task-level with the proposed ConditionNet, which will be used to adapt the parameters of the basic SR network (BaseNet).
Learning Intents behind Interactions with Knowledge Graph for Recommendation
In this study, we explore intents behind a user-item interaction by using auxiliary item knowledge, and propose a new model, Knowledge Graph-based Intent Network (KGIN).
Advances and Challenges in Conversational Recommender Systems: A Survey
In this paper, we provide a systematic review of the techniques used in current CRSs.
Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering
Open-domain Question Answering (OpenQA) is an important task in Natural Language Processing (NLP), which aims to answer a question in the form of natural language based on large-scale unstructured documents.
Machine Reading Comprehension
Open-Domain Question Answering
Causal Screening to Interpret Graph Neural Networks
In this work, we focus on the causal interpretability in GNNs and propose a method, Causal Screening, from the perspective of cause-effect.
Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction
In this paper, we propose a general approach to learn relation prototypesfrom unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient trainingdata.
Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method
To this end, we analyze the working mechanism of GCN with causal graph, estimating the causal effect of a node's local structure for the prediction.
Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment
GNN-based EA methods present promising performances by modeling the KG structure defined by relation triples.
Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue
However, we argue that there is a significant gap between clicks and user satisfaction -- it is common that a user is "cheated" to click an item by the attractive title/cover of the item.
Multi-modal Cooking Workflow Construction for Food Recipes
Understanding food recipe requires anticipating the implicit causal effects of cooking actions, such that the recipe can be converted into a graph describing the temporal workflow of the recipe.
Neural Sparse Voxel Fields
We also demonstrate several challenging tasks, including multi-scene learning, free-viewpoint rendering of a moving human, and large-scale scene rendering.
Visual Relation Grounding in Videos
In this paper, we explore a novel task named visual Relation Grounding in Videos (vRGV).
Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval
To facilitate video retrieval with complex queries, we propose a Tree-augmented Cross-modal Encoding method by jointly learning the linguistic structure of queries and the temporal representation of videos.
Disentangled Graph Collaborative Filtering
Such uniform approach to model user interests easily results in suboptimal representations, failing to model diverse relationships and disentangle user intents in representations.
Interactive Path Reasoning on Graph for Conversational Recommendation
Traditional recommendation systems estimate user preference on items from past interaction history, thus suffering from the limitations of obtaining fine-grained and dynamic user preference.
Few-shot 3D Point Cloud Semantic Segmentation
These fully supervised approaches heavily rely on large amounts of labeled training data that are difficult to obtain and cannot segment new classes after training.
Few-shot 3D Point Cloud Semantic Segmentation
Semantic Segmentation
Denoising Implicit Feedback for Recommendation
In this work, we explore the central theme of denoising implicit feedback for recommender training.
Rethinking Dialogue State Tracking with Reasoning
Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management.
Hierarchical Fashion Graph Network for Personalized Outfit Recommendation
Fashion outfit recommendation has attracted increasing attentions from online shopping services and fashion communities. Distinct from other scenarios (e. g., social networking or content sharing) which recommend a single item (e. g., a friend or picture) to a user, outfit recommendation predicts user preference on a set of well-matched fashion items. Hence, performing high-quality personalized outfit recommendation should satisfy two requirements -- 1) the nice compatibility of fashion items and 2) the consistence with user preference.
Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-Start Users
In this work, we consider the conversational recommendation for cold-start users, where a system can both ask the attributes from and recommend items to a user interactively.
Knowledge Enhanced Neural Fashion Trend Forecasting
Further-more, to effectively model the time series data of fashion elements with rather complex patterns, we propose a Knowledge EnhancedRecurrent Network model (KERN) which takes advantage of the capability of deep recurrent neural networks in modeling time-series data.
Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen
The curse of knowledge can impede communication between experts and laymen.
Semantic Graphs for Generating Deep Questions
This paper proposes the problem of Deep Question Generation (DQG), which aims to generate complex questions that require reasoning over multiple pieces of information of the input passage.
Learning Goal-oriented Dialogue Policy with Opposite Agent Awareness
Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment.
Reinforced Negative Sampling over Knowledge Graph for Recommendation
Properly handling missing data is a fundamental challenge in recommendation.
Cross-GCN: Enhancing Graph Convolutional Network with $k$-Order Feature Interactions
Graph Convolutional Network (GCN) is an emerging technique that performs learning and reasoning on graph data.
Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems
Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models.
Multi-source Domain Adaptation for Visual Sentiment Classification
Existing domain adaptation methods on visual sentiment classification typically are investigated under the single-source scenario, where the knowledge learned from a source domain of sufficient labeled data is transferred to the target domain of loosely labeled or unlabeled data.
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
The performance of existing point cloud-based 3D object detection methods heavily relies on large-scale high-quality 3D annotations.
Heuristic Black-box Adversarial Attacks on Video Recognition Models
To overcome this challenge, we propose a heuristic black-box attack model that generates adversarial perturbations only on the selected frames and regions.
Mining Unfollow Behavior in Large-Scale Online Social Networks via Spatial-Temporal Interaction
Next, we define user's attributes as two categories: spatial attributes (e. g., social role of user) and temporal attributes (e. g., post content of user).
Semi-supervised Entity Alignment via Joint Knowledge Embedding Model and Cross-graph Model
Specifically, as for the knowledge embedding model, we utilize TransE to implicitly complete two KGs towards consistency and learn relational constraints between entities.
Meta-Transfer Learning through Hard Tasks
In this paper, we propose a novel approach called meta-transfer learning (MTL) which learns to transfer the weights of a deep NN for few-shot learning tasks.
Multi-Channel Graph Neural Network for Entity Alignment
Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments.
Ranked #30 on
Entity Alignment
on DBP15k zh-en
Low-Resource Name Tagging Learned with Weakly Labeled Data
Name tagging in low-resource languages or domains suffers from inadequate training data.
PS^2-Net: A Locally and Globally Aware Network for Point-Based Semantic Segmentation
In this paper, we present the PS^2-Net -- a locally and globally aware deep learning framework for semantic segmentation on 3D scene-level point clouds.
Who, Where, and What to Wear? Extracting Fashion Knowledge from Social Media
We unify three tasks of occasion, person and clothing discovery from multiple modalities of images, texts and metadata.
Automatic Fashion Knowledge Extraction from Social Media
Fashion knowledge plays a pivotal role in helping people in their dressing.
Modeling Embedding Dimension Correlations via Convolutional Neural Collaborative Filtering
In this work, we emphasize on modeling the correlations among embedding dimensions in neural networks to pursue higher effectiveness for CF.
Deep Conversational Recommender in Travel
When traveling to a foreign country, we are often in dire need of an intelligent conversational agent to provide instant and informative responses to our various queries.
Learning to Self-Train for Semi-Supervised Few-Shot Classification
On each task, we train a few-shot model to predict pseudo labels for unlabeled data, and then iterate the self-training steps on labeled and pseudo-labeled data with each step followed by fine-tuning.
Recent Advances in Neural Question Generation
Emerging research in Neural Question Generation (NQG) has started to integrate a larger variety of inputs, and generating questions requiring higher levels of cognition.
KGAT: Knowledge Graph Attention Network for Recommendation
To provide more accurate, diverse, and explainable recommendation, it is compulsory to go beyond modeling user-item interactions and take side information into account.
Ranked #2 on
Link Prediction
on Yelp
Neural Graph Collaborative Filtering
Further analysis verifies the importance of embedding propagation for learning better user and item representations, justifying the rationality and effectiveness of NGCF.
Ranked #6 on
Link Prediction
on MovieLens 25M
Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure
Adversarial Training (AT), a dynamic regularization technique, can resist the worst-case perturbations on input features and is a promising choice to improve model robustness and generalization.
Ranked #3 on
Node Classification
on NELL
Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
In this paper, we jointly learn the model of recommendation and knowledge graph completion.
Ranked #1 on
Knowledge Graph Completion
on DBbook2014
Graph Neural Networks with Generated Parameters for Relation Extraction
Recently, progress has been made towards improving relational reasoning in machine learning field.
Learning a Disentangled Embedding for Monocular 3D Shape Retrieval and Pose Estimation
We propose a novel approach to jointly perform 3D shape retrieval and pose estimation from monocular images. In order to make the method robust to real-world image variations, e. g. complex textures and backgrounds, we learn an embedding space from 3D data that only includes the relevant information, namely the shape and pose.
Meta-Transfer Learning for Few-Shot Learning
In this paper we propose a novel few-shot learning method called meta-transfer learning (MTL) which learns to adapt a deep NN for few shot learning tasks.
