Method and apparatus for processing video signal using graph-based transform

The present invention relates to a method for decoding a video signal using a graph-based transform, the method comprising: a step of extracting prediction unit partition information of a current coding unit from the video signal; a step of acquiring a graph-based transform kernel from pre-set table information on the basis of the prediction unit partition information; and a step of performing an inverse transform with respect to a transform unit using the graph-based transform kernel, wherein the graph-based transform kernel corresponds to at least one of the prediction unit partition information or an edge weight, and the edge weight is a pre-set value representing the correlation between pixels.