Soo-Hyun Choi

Samsung | samsung · Mobile Communications

Graph neural networks (GNNs) have received remarkable success in link prediction (GNNLP) tasks. Existing efforts first predefine the subgraph for the whole dataset and then apply GNNs to encode edge representations by leveraging the neighborhood structure induced by the fixed subgraph. The prominence of GNNLP methods significantly relies on the adh...

Real-time bidding (RTB) has become a major paradigm of display advertising. Each ad impression generated from a user visit is auctioned in real time, where demand-side platform (DSP) automatically provides bid price usually relying on the ad impression value estimation and the optimal bid price determination. However, the current bid strategy overl...

Learning useful interactions between input features is crucial for tabular data modeling. Recent efforts start to explicitly model the feature interactions with graph, where each feature is treated as an individual node. However, the existing graph construction methods either heuristically formulate a fixed feature-interaction graph based on specif...

We introduce a novel masked graph autoencoder (MGAE) framework to perform effective learning on graph structure data. Taking insights from self-supervised learning, we randomly mask a large proportion of edges and try to reconstruct these missing edges during training. MGAE has two core designs. First, we find that masking a high ratio of the input...

Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains. To handle large-scale graphs, most of the existing methods partition the input graph into multiple sub-graphs (e.g., through node clustering) and apply batch trai...

Graph neural networks (GNNs) integrate deep architectures and topological structure modeling in an effective way. However, the performance of existing GNNs would decrease significantly when they stack many layers, because of the over-smoothing issue. Node embeddings tend to converge to similar vectors when GNNs keep recursively aggregating the repr...

Recommender systems play a fundamental role in web applications in filtering massive information and matching user interests. While many efforts have been devoted to developing more effective models in various scenarios, the exploration on the explainability of recommender systems is running behind. Explanations could help improve user experience a...

Real-time bidding (RTB) that features per-impression-level real-time ad auctions has become a popular practice in today's digital advertising industry. In RTB, click-through rate (CTR) prediction is a fundamental problem to ensure the success of an ad campaign and boost revenue. In this paper, we present a dynamic CTR prediction model designed for...

The Internet is getting richer, and so the services. The richer the services, the more the users demand. The more they demand, the more we guarantee(1). This thesis investigates the congestion control mechanisms for interactive multimedia streaming applications. We start by raising a question as to why the congestion control schemes are not widely...

Real-time multimedia applications prefer smooth and pre- dictable throughput to TCP-like abrupt sending rate changes, and this led to the development of TCP-Friendly Rate-based Congestion Control (TFRC). However, we observed a long- term throughput imbalance between TFRC and TCP sources, especially under a low level of statistical multiplexing. We...

During the past few years, design of experiments (DOE) has been gaining acceptance in the telecommunications research community as a mean for designing and analyzing experiments economically and efficiently. In addition, the need for introducing a systematic robust design methodology (i.e., one of the most popular DOE methodologies) to network simu...

The RFID technology has ample growth potential since it can be applied to practically all areas, ranging from retail and logistics sectors to livestock management, home network systems, traffic control and hospital patient management. With the advent of this technology, it is possible to realize ubiquitous sensor network (USN) such that every objec...

We present TFWC, a TCP-friendly window-based conges- tion control mechanism for real-time multimedia streaming applications. Although TFRC is regarded as a de facto stan- dard for those types of applications, under low stat-mux con- ditions fairness can be an issue. We re-introduce a TCP-like ACK mechanism while retaining the TCP throughput equa- t...

The current congestion control mechanisms for the Internet date back to the early 1980’s and were primarily designed to stop congestion collapse with the typical traffic of that era. In recent years the amount of traffic generated by real-time multimedia applications has substantially increased, and the existing congestion control often does not op...

This paper summarizes the present state of optical networking, whereabouts of the optical network by which IP-centric networks carry the traffic. By start out from the assuming that the Internet transport infrastructure is moving towards a model of high speed routers interconnected by optical core networks, various technical issues mainly on optica...

It is well known that real-time multimedia applications pre- fer smooth and predictable throughput to a TCP-like abrupt sending rate change. The current release of VIC/RAT oper- ates just on top of the RTP/RTCP architecture over UDP protocol, not providing a fine-grained congestion control for its real-time interactive streaming flows. This may wor...