Total: 31
Explainable reinforcement learning (XRL) methods aim to help elucidate agent policies and decision-making processes. The majority of XRL approaches focus on local explanations, seeking to shed light on the reasons an agent acts the way it does at a specific world state. While such explanations are both useful and necessary, they typically do not portray the outcomes of the agent's selected choice of action. In this work, we propose ``COViz'', a new local explanation method that visually compares the outcome of an agent's chosen action to a counterfactual one. In contrast to most local explanations that provide state-limited observations of the agent's motivation, our method depicts alternative trajectories the agent could have taken from the given state and their outcomes. We evaluated the usefulness of COViz in supporting people's understanding of agents' preferences and compare it with reward decomposition, a local explanation method that describes an agent's expected utility for different actions by decomposing it into meaningful reward types. Furthermore, we examine the complementary benefits of integrating both methods. Our results show that such integration significantly improved participants' performance.
Inferring the private information of humans from their strategic behavioral data is crucial and challenging. The main approach is first obtaining human behavior functions (which map public information and human private information to behavior), enabling subsequent inference of private information from observed behavior. Most existing studies rely on strong equilibrium assumptions to obtain behavior functions. Our work focuses on continuous double auctions, where multiple traders with heterogeneous rationalities and beliefs dynamically trade commodities and deriving equilibria is generally intractable. We develop a knowledge-aware machine learning-based framework to infer each trader's private cost vectors for producing different units of its commodity. Our key idea is to learn behavior functions by incorporating the statistical knowledge about private costs given the observed trader asking behavior across the population. Specifically, we first use a neural network to characterize each trader's behavior function. Second, we leverage the statistical knowledge to derive the posterior distribution of each trader's private costs given its observed asks. Third, through designing a novel loss function, we utilize the knowledge-based posterior distributions to guide the learning of the neural network. We conduct extensive experiments on a large experimental dataset, and demonstrate the superior performance of our framework over baselines in inferring the private information of humans.
Level generation is a central focus of Procedural Content Generation (PCG), yet deep learning-based approaches are limited by scarce training data, i.e., human-designed levels. Despite being a dominant framework, Generative Adversarial Networks (GANs) exhibit a substantial quality gap between generated and human-authored levels, alongside rising training costs, particularly with increasing token complexity. In this paper, we introduce a diffusion-based generative model that learns from just one example. Our approach involves two core components: 1) an efficient yet expressive level representation, and 2) a latent denoising network with constrained receptive fields. To start with, our method utilizes token semantic labels, similar to word embeddings, to provide dense representations. This strategy not only surpasses one-hot encoding in representing larger game levels but also improves stability and accelerates convergence in latent diffusion. In addition, we adapt the denoising network architecture to confine the receptive field to localized patches of the data, aiming to facilitate single-example learning. Extensive experiments demonstrate that our model is capable of generating stylistically congruent samples of arbitrary sizes compared to manually designed levels. It suits a wide range of level structures with fewer artifacts than GAN-based approaches. The source code is available at https://github.com/shiqi-dai/diffusioncraft.
Historically, much of machine learning research has focused on the performance of the algorithm alone, but recently more attention has been focused on optimizing joint human-algorithm performance. Here, we analyze a specific type of human-algorithm collaboration where the algorithm has access to a set of n items, and presents a subset of size k to the human, who selects a final item from among those k. This scenario could model content recommendation, route planning, or any type of labeling task. Because both the human and algorithm have imperfect, noisy information about the true ordering of items, the key question is: which value of k maximizes the probability that the best item will be ultimately selected? For k=1, performance is optimized by the algorithm acting alone, and for k=n it is optimized by the human acting alone. Surprisingly, we show that for multiple of noise models, it is optimal to set k in [2, n-1] - that is, there are strict benefits to collaborating, even when the human and algorithm have equal accuracy separately. We demonstrate this theoretically for the Mallows model and experimentally for the Random Utilities models of noisy permutations. However, we show this pattern is *reversed* when the human is anchored on the algorithm's presented ordering - the joint system always has strictly worse performance. We extend these results to the case where the human and algorithm differ in their accuracy levels, showing that there always exist regimes where a more accurate agent would strictly benefit from collaborating with a less accurate one, but these regimes are asymmetric between the human and the algorithm's accuracy.
Neuroscience research indicates that the interaction among different functional regions of the brain plays a crucial role in driving various cognitive tasks. Existing studies have primarily focused on constructing either local or global functional connectivity maps within the brain, often lacking an adaptive approach to fuse functional brain regions and explore latent relationships between localization during different cognitive tasks. This paper introduces a novel approach called the Local-Ascending-Global Learning Strategy (LAG) to uncover higher-level latent topological patterns among functional brain regions. The strategy initiates from the local connectivity of individual brain functional regions and develops a K-Level Self-Adaptive Ascending Network (SALK) to dynamically capture strong connectivity patterns among brain regions during different cognitive tasks. Through the step-by-step fusion of brain regions, this approach captures higher-level latent patterns, shedding light on the progressively adaptive fusion of various brain functional regions under different cognitive tasks. Notably, this study represents the first exploration of higher-level latent patterns through progressively adaptive fusion of diverse brain functional regions under different cognitive tasks. The proposed LAG strategy is validated using datasets related to fatigue (SEED-VIG), emotion (SEED-IV), and motor imagery (BCI_C_IV_2a). The results demonstrate the generalizability of LAG, achieving satisfactory outcomes in independent-subject experiments across all three datasets. This suggests that LAG effectively characterizes higher-level latent patterns associated with different cognitive tasks, presenting a novel approach to understanding brain patterns in varying cognitive contexts.
Working memory is a critical aspect of both human intelligence and artificial intelligence, serving as a workspace for the temporary storage and manipulation of information. In this paper, we systematically assess the working memory capacity of ChatGPT, a large language model developed by OpenAI, by examining its performance in verbal and spatial n-back tasks under various conditions. Our experiments reveal that ChatGPT has a working memory capacity limit strikingly similar to that of humans. Furthermore, we investigate the impact of different instruction strategies on ChatGPT's performance and observe that the fundamental patterns of a capacity limit persist. From our empirical findings, we propose that n-back tasks may serve as tools for benchmarking the working memory capacity of large language models and hold potential for informing future efforts aimed at enhancing AI working memory.
This paper addresses the task of counting human actions of interest using sensor data from wearable devices. We propose a novel exemplar-based framework, allowing users to provide exemplars of the actions they want to count by vocalizing predefined sounds ``one'', ``two'', and ``three''. Our method first localizes temporal positions of these utterances from the audio sequence. These positions serve as the basis for identifying exemplars representing the action class of interest. A similarity map is then computed between the exemplars and the entire sensor data sequence, which is further fed into a density estimation module to generate a sequence of estimated density values. Summing these density values provides the final count. To develop and evaluate our approach, we introduce a diverse and realistic dataset consisting of real-world data from 37 subjects and 50 action categories, encompassing both sensor and audio data. The experiments on this dataset demonstrate the viability of the proposed method in counting instances of actions from new classes and subjects that were not part of the training data. On average, the discrepancy between the predicted count and the ground truth value is 7.47, significantly lower than the errors of the frequency-based and transformer-based methods. Our project, code and dataset can be found at https://github.com/cvlab-stonybrook/ExRAC.
We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work assumes that human preferences are generated based only upon the reward accrued within those segments, or their partial return. Recent work casts doubt on the validity of this assumption, proposing an alternative preference model based upon regret. We investigate the consequences of assuming preferences are based upon partial return when they actually arise from regret. We argue that the learned function is an approximation of the optimal advantage function, not a reward function. We find that if a specific pitfall is addressed, this incorrect assumption is not particularly harmful, resulting in a highly shaped reward function. Nonetheless, this incorrect usage of the approximation of the optimal advantage function is less desirable than the appropriate and simpler approach of greedy maximization of it. From the perspective of the regret preference model, we also provide a clearer interpretation of fine tuning contemporary large language models with RLHF. This paper overall provides insight regarding why learning under the partial return preference model tends to work so well in practice, despite it conforming poorly to how humans give preferences.
Multimodal Sentiment Analysis (MSA) has attracted widespread research attention recently. Most MSA studies are based on the assumption of modality completeness. However, many inevitable factors in real-world scenarios lead to uncertain missing modalities, which invalidate the fixed multimodal fusion approaches. To this end, we propose a Unified multimodal Missing modality self-Distillation Framework (UMDF) to handle the problem of uncertain missing modalities in MSA. Specifically, a unified self-distillation mechanism in UMDF drives a single network to automatically learn robust inherent representations from the consistent distribution of multimodal data. Moreover, we present a multi-grained crossmodal interaction module to deeply mine the complementary semantics among modalities through coarse- and fine-grained crossmodal attention. Eventually, a dynamic feature integration module is introduced to enhance the beneficial semantics in incomplete modalities while filtering the redundant information therein to obtain a refined and robust multimodal representation. Comprehensive experiments on three datasets demonstrate that our framework significantly improves MSA performance under both uncertain missing-modality and complete-modality testing conditions.
With the rapid development of AI-based decision aids, different forms of AI assistance have been increasingly integrated into the human decision making processes. To best support humans in decision making, it is essential to quantitatively understand how diverse forms of AI assistance influence humans' decision making behavior. To this end, much of the current research focuses on the end-to-end prediction of human behavior using ``black-box'' models, often lacking interpretations of the nuanced ways in which AI assistance impacts the human decision making process. Meanwhile, methods that prioritize the interpretability of human behavior predictions are often tailored for one specific form of AI assistance, making adaptations to other forms of assistance difficult. In this paper, we propose a computational framework that can provide an interpretable characterization of the influence of different forms of AI assistance on decision makers in AI-assisted decision making. By conceptualizing AI assistance as the ``nudge'' in human decision making processes, our approach centers around modelling how different forms of AI assistance modify humans' strategy in weighing different information in making their decisions. Evaluations on behavior data collected from real human decision makers show that the proposed framework outperforms various baselines in accurately predicting human behavior in AI-assisted decision making. Based on the proposed framework, we further provide insights into how individuals with different cognitive styles are nudged by AI assistance differently.
Performing person detection in super-high-resolution images has been a challenging task. For such a task, modern detectors, which usually encode a box using center and width/height, struggle with accuracy due to two factors: 1) Human characteristic: people come in various postures and the center with high freedom is difficult to capture robust visual pattern; 2) Image characteristic: due to vast scale diversity of input (gigapixel-level), distance regression (for width and height) is hard to pinpoint, especially for a person, with substantial scale, who is near the camera. To address these challenges, we propose GigaHumanDet, an innovative solution aimed at further enhancing detection accuracy for gigapixel-level images. GigaHumanDet employs the corner modeling method to avoid the potential issues of a high degree of freedom in center pinpointing. To better distinguish similar-looking persons and enforce instance consistency of corner pairs, an instance-guided learning approach is designed to capture discriminative individual semantics. Further, we devise reliable shape-aware bodyness equipped with a multi-precision strategy as the human corner matching guidance to be appropriately adapted to the single-view large scene. Experimental results on PANDA and STCrowd datasets show the superiority and strong applicability of our design. Notably, our model achieves 82.4% in term of AP, outperforming current state-of-the-arts by more than 10%.
With the strong robusticity on illumination variations, near-infrared (NIR) can be an effective and essential complement to visible (VIS) facial expression recognition in low lighting or complete darkness conditions. However, facial expression recognition (FER) from NIR images presents a more challenging problem than traditional FER due to the limitations imposed by the data scale and the difficulty of extracting discriminative features from incomplete visible lighting contents. In this paper, we give the first attempt at deep NIR facial expression recognition and propose a novel method called near-infrared facial expression transformer (NFER-Former). Specifically, to make full use of the abundant label information in the field of VIS, we introduce a Self-Attention Orthogonal Decomposition mechanism that disentangles the expression information and spectrum information from the input image, so that the expression features can be extracted without the interference of spectrum variation. We also propose a Hypergraph-Guided Feature Embedding method that models some key facial behaviors and learns the structure of the complex correlations between them, thereby alleviating the interference of inter-class similarity. Additionally, we construct a large NIR-VIS Facial Expression dataset that includes 360 subjects to better validate the efficiency of NFER-Former. Extensive experiments and ablation studies show that NFER-Former significantly improves the performance of NIR FER and achieves state-of-the-art results on the only two available NIR FER datasets, Oulu-CASIA and Large-HFE.
While the question of misspecified objectives has gotten much attention in recent years, most works in this area primarily focus on the challenges related to the complexity of the objective specification mechanism (for example, the use of reward functions). However, the complexity of the objective specification mechanism is just one of many reasons why the user may have misspecified their objective. A foundational cause for misspecification that is being overlooked by these works is the inherent asymmetry in human expectations about the agent's behavior and the behavior generated by the agent for the specified objective. To address this, we propose a novel formulation for the objective misspecification problem that builds on the human-aware planning literature, which was originally introduced to support explanation and explicable behavioral generation. Additionally, we propose a first-of-its-kind interactive algorithm that is capable of using information generated under incorrect beliefs about the agent to determine the true underlying goal of the user.
Crowdsourcing platforms use various truth discovery algorithms to aggregate annotations from multiple labelers. In an online setting, however, the main challenge is to decide whether to ask for more annotations for each item to efficiently trade off cost (i.e., the number of annotations) for quality of the aggregated annotations. In this paper, we propose a novel approach for general complex annotation (such as bounding boxes and taxonomy paths), that works in an online crowdsourcing setting. We prove that the expected average similarity of a labeler is linear in their accuracy conditional on the reported label. This enables us to infer reported label accuracy in a broad range of scenarios. We conduct extensive evaluations on real-world crowdsourcing data from Meta and show the effectiveness of our proposed online algorithms in improving the cost-quality trade-off.
Preference-based Reinforcement Learning (PbRL) enables non-experts to train Reinforcement Learning models using preference feedback. However, the effort required to collect preference labels from real humans means that PbRL research primarily relies on synthetic labellers. We validate the most common synthetic labelling strategy by comparing against labels collected from a crowd of humans on three Deep Mind Control (DMC) suite tasks: stand, walk, and run. We find that: (1) the synthetic labels are a good proxy for real humans under some circumstances, (2) strong preference label agreement between human and synthetic labels is not necessary for similar policy performance, (3) policy performance is higher at the start of training from human feedback and is higher at the end of training from synthetic feedback, and (4) training on only examples with high levels of inter-annotator agreement does not meaningfully improve policy performance. Our results justify the use of synthetic labellers to develop and ablate PbRL methods, and provide insight into how human labelling changes over the course of policy training.
AI powered code-recommendation systems, such as Copilot and CodeWhisperer, provide code suggestions inside a programmer's environment (e.g., an IDE) with the aim of improving productivity. We pursue mechanisms for leveraging signals about programmers' acceptance and rejection of code suggestions to guide recommendations. We harness data drawn from interactions with GitHub Copilot, a system used by millions of programmers, to develop interventions that can save time for programmers. We introduce a utility-theoretic framework to drive decisions about suggestions to display versus withhold. The approach, conditional suggestion display from human feedback (CDHF), relies on a cascade of models that provide the likelihood that recommended code will be accepted. These likelihoods are used to selectively hide suggestions, reducing both latency and programmer verification time. Using data from 535 programmers, we perform a retrospective evaluation of CDHF and show that we can avoid displaying a significant fraction of suggestions that would have been rejected. We further demonstrate the importance of incorporating the programmer's latent unobserved state in decisions about when to display suggestions through an ablation study. Finally, we showcase how using suggestion acceptance as a reward signal for guiding the display of suggestions can lead to suggestions of reduced quality, indicating an unexpected pitfall.
Multi-agent trajectory prediction is crucial for various practical applications, spurring the construction of many large-scale trajectory datasets, including vehicles and pedestrians. However, discrepancies exist among datasets due to external factors and data acquisition strategies. External factors include geographical differences and driving styles, while data acquisition strategies include data acquisition rate, history/prediction length, and detector/tracker error. Consequently, the proficient performance of models trained on large-scale datasets has limited transferability on other small-size datasets, bounding the utilization of existing large-scale datasets. To address this limitation, we propose a method based on continuous and stochastic representations of Neural Stochastic Differential Equations (NSDE) for alleviating discrepancies due to data acquisition strategy. We utilize the benefits of continuous representation for handling arbitrary time steps and the use of stochastic representation for handling detector/tracker errors. Additionally, we propose a dataset-specific diffusion network and its training framework to handle dataset-specific detection/tracking errors. The effectiveness of our method is validated against state-of-the-art trajectory prediction models on the popular benchmark datasets: nuScenes, Argoverse, Lyft, INTERACTION, and Waymo Open Motion Dataset (WOMD). Improvement in performance gain on various source and target dataset configurations shows the generalized competence of our approach in addressing cross-dataset discrepancies.
Video highlights detection (VHD) is an active research field in computer vision, aiming to locate the most user-appealing clips given raw video inputs. However, most VHD methods are based on the closed world assumption, i.e., a fixed number of highlight categories is defined in advance and all training data are available beforehand. Consequently, existing methods have poor scalability with respect to increasing highlight domains and training data. To address above issues, we propose a novel video highlights detection method named Global Prototype Encoding (GPE) to learn incrementally for adapting to new domains via parameterized prototypes. To facilitate this new research direction, we collect a finely annotated dataset termed LiveFood, including over 5,100 live gourmet videos that consist of four domains: ingredients, cooking, presentation, and eating. To the best of our knowledge, this is the first work to explore video highlights detection in the incremental learning setting, opening up new land to apply VHD for practical scenarios where both the concerned highlight domains and training data increase over time. We demonstrate the effectiveness of GPE through extensive experiments. Notably, GPE surpasses popular domain incremental learning methods on LiveFood, achieving significant mAP improvements on all domains. Concerning the classic datasets, GPE also yields comparable performance as previous arts. The code is available at: https://github.com/ForeverPs/IncrementalVHD_GPE.
We consider the problem of personalizing audio to maximize user experience. Briefly, we aim to find a filter h*, which applied to any music or speech, will maximize the user’s satisfaction. This is a black-box optimization problem since the user’s satisfaction function is unknown. Substantive work has been done on this topic where the key idea is to play audio samples to the user, each shaped by a different filter hi, and query the user for their satisfaction scores f(hi). A family of “surrogate” functions is then designed to fit these scores and the optimization method gradually refines these functions to arrive at the filter ˆh* that maximizes satisfaction. In certain applications, we observe that a second type of querying is possible where users can tell us the individual elements h*[j] of the optimal filter h*. Consider an analogy from cooking where the goal is to cook a recipe that maximizes user satisfaction. A user can be asked to score various cooked recipes (e.g., tofu fried rice) or to score individual ingredients (say, salt, sugar, rice, chicken, etc.). Given a budget of B queries, where a query can be of either type, our goal is to find the recipe that will maximize this user’s satisfaction. Our proposal builds on Sparse Gaussian Process Regression (GPR) and shows how a hybrid approach can outperform any one type of querying. Our results are validated through simulations and real world experiments, where volunteers gave feedback on music/speech audio and were able to achieve high satisfaction levels. We believe this idea of hybrid querying opens new problems in black-box optimization and solutions can benefit other applications beyond audio personalization.
This paper focuses in the inherent anchoring bias present in sequential reviews-sentiment corpora annotation processes. It proposes employing a limited subset of meticulously chosen reviews at the outset of the process, as a means of calibration, effectively mitigating the phenomenon. Through extensive experimentation we validate the phenomenon of sentiment bias in the annotation process and show that its magnitude can be influenced by pre-calibration. Furthermore, we show that the choice of the calibration set matters, hence the need for effective guidelines for choosing the reviews to be included in it. A comparison of annotators performance with the proposed calibration to annotation processes that do not use calibration or use a randomly-picked calibration set, reveals that indeed the calibration set picked is highly effective---it manages to substantially reduce the average absolute error compared to the other cases. Furthermore, the proposed selection guidelines are found to be highly robust in picking an effective calibration set also for domains different than the one based on which these rules were extracted.
Gaze object prediction aims to predict the location and category of the object that is watched by a human. Previous gaze object prediction works use CNN-based object detectors to predict the object's location. However, we find that Transformer-based object detectors can predict more accurate object location for dense objects in retail scenarios. Moreover, the long-distance modeling capability of the Transformer can help to build relationships between the human head and the gaze object, which is important for the GOP task. To this end, this paper introduces Transformer into the fields of gaze object prediction and proposes an end-to-end Transformer-based gaze object prediction method named TransGOP. Specifically, TransGOP uses an off-the-shelf Transformer-based object detector to detect the location of objects and designs a Transformer-based gaze autoencoder in the gaze regressor to establish long-distance gaze relationships. Moreover, to improve gaze heatmap regression, we propose an object-to-gaze cross-attention mechanism to let the queries of the gaze autoencoder learn the global-memory position knowledge from the object detector. Finally, to make the whole framework end-to-end trained, we propose a Gaze Box loss to jointly optimize the object detector and gaze regressor by enhancing the gaze heatmap energy in the box of the gaze object. Extensive experiments on the GOO-Synth and GOO-Real datasets demonstrate that our TransGOP achieves state-of-the-art performance on all tracks, i.e., object detection, gaze estimation, and gaze object prediction. Our code will be available at https://github.com/chenxi-Guo/TransGOP.git.
Composite images (CIs) typically combine various elements from different scenes, views, and styles, which are a very important information carrier in the era of mixed media such as virtual reality, mixed reality, metaverse, etc. However, the complexity of CI content presents a significant challenge for subsequent visual perception modeling and compression. In addition, the lack of benchmark CI databases also hinders the use of recent advanced data-driven methods. To address these challenges, we first establish one of the earliest visual redundancy prediction (VRP) databases for CIs. Moreover, we propose a multi-visual effect (MVE)-driven incremental learning method that combines the strengths of hand-crafted and data-driven approaches to achieve more accurate VRP modeling. Specifically, we design special incremental rules to learn the visual knowledge flow of MVE. To effectively capture the associated features of MVE, we further develop a three-stage incremental learning approach for VRP based on an encoder-decoder network. Extensive experimental results validate the superiority of the proposed method in terms of subjective, objective, and compression experiments.
Fashion image editing aims to edit an input image to obtain richer or distinct visual clothing matching effects. Existing global fashion image editing methods are difficult to achieve rich outfit combination effects while local fashion image editing is more in line with the needs of diverse and personalized outfit matching. The local editing techniques typically depend on text and auxiliary modalities (e.g., human poses, human keypoints, garment sketches, etc.) for image manipulation, where the auxiliary modalities essentially assist in locating the editing region. Since these auxiliary modalities usually involve additional efforts in practical application scenarios, text-driven fashion image editing shows high flexibility. In this paper, we propose TexFit, a Text-driven Fashion image Editing method using diffusion models, which performs the local image editing only with the easily accessible text. Our approach employs a text-based editing region location module to predict precise editing region in the fashion image. Then, we take the predicted region as the generation condition of diffusion models together with the text prompt to achieve precise local editing of fashion images while keeping the rest part intact. In addition, previous fashion datasets usually focus on global description, lacking local descriptive information that can guide the precise local editing. Therefore, we develop a new DFMM-Spotlight dataset by using region extraction and attribute combination strategies. It focuses locally on clothes and accessories, enabling local editing with text input. Experimental results on the DFMM-Spotlight dataset demonstrate the effectiveness of our model. Code and Datasets are available at https://texfit.github.io/.
This paper develops a novel rating-based reinforcement learning approach that uses human ratings to obtain human guidance in reinforcement learning. Different from the existing preference-based and ranking-based reinforcement learning paradigms, based on human relative preferences over sample pairs, the proposed rating-based reinforcement learning approach is based on human evaluation of individual trajectories without relative comparisons between sample pairs. The rating-based reinforcement learning approach builds on a new prediction model for human ratings and a novel multi-class loss function. We conduct several experimental studies based on synthetic ratings and real human ratings to evaluate the effectiveness and benefits of the new rating-based reinforcement learning approach.
Taking incompatible multiple drugs together may cause adverse interactions and side effects on the body. Accurate prediction of drug-drug interaction (DDI) events is essential for avoiding this issue. Recently, various artificial intelligence-based approaches have been proposed for predicting DDI events. However, DDI events are associated with complex relationships and mechanisms among drugs, targets, enzymes, transporters, molecular structures, etc. Existing approaches either partially or loosely consider these relationships and mechanisms by a non-end-to-end learning framework, resulting in sub-optimal feature extractions and fusions for prediction. Different from them, this paper proposes a Multimodal Knowledge Graph Fused End-to-end Neural Network (MKGFENN) that consists of two main parts: multimodal knowledge graph (MKG) and fused end-to-end neural network (FENN). First, MKG is constructed by comprehensively exploiting DDI events-associated relationships and mechanisms from four knowledge graphs of drugs-chemical entities, drug-substructures, drugs-drugs, and molecular structures. Correspondingly, a four channels graph neural network is designed to extract high-order and semantic features from MKG. Second, FENN designs a multi-layer perceptron to fuse the extracted features by end-to-end learning. With such designs, the feature extractions and fusions of DDI events are guaranteed to be comprehensive and optimal for prediction. Through extensive experiments on real drug datasets, we demonstrate that MKG-FENN exhibits high accuracy and significantly outperforms state-of-the-art models in predicting DDI events. The source code and supplementary file of this article are available on: https://github.com/wudi1989/MKG-FENN.